diff --git a/.gitignore b/.gitignore
index 7d14fdee..9a2c5bda 100644
--- a/.gitignore
+++ b/.gitignore
@@ -19,7 +19,7 @@
 
 # Project
 **/*.json
-**/.bin
+**/*.bin
 *.npy
 input.txt
 output.txt
diff --git a/doc/Gpx_Tutorial.ipynb b/doc/Gpx_Tutorial.ipynb
index 6e6d7332..5d91ae32 100644
--- a/doc/Gpx_Tutorial.ipynb
+++ b/doc/Gpx_Tutorial.ipynb
@@ -23,18 +23,9 @@
    "execution_count": 1,
    "id": "33b7dcca",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Requirement already satisfied: egobox in d:\\rlafage\\miniconda3\\lib\\site-packages (0.23.0)\n",
-      "Note: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "%pip install egobox"
+    "# %pip install egobox"
    ]
   },
   {
@@ -53,7 +44,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import egobox as egx"
+    "import egobox as egx\n",
+    "\n",
+    "# To display debug information (none by default)\n",
+    "# import logging\n",
+    "# logging.basicConfig(level=logging.DEBUG)"
    ]
   },
   {
@@ -96,8 +91,8 @@
    "source": [
     "import numpy as np\n",
     "\n",
-    "xt = np.array([[0.0, 1.0, 2.0, 3.0, 4.0]]).T\n",
-    "yt = np.array([[0.0, 1.0, 1.5, 0.9, 1.0]]).T"
+    "xt = np.array([0.0, 1.0, 2.0, 3.0, 4.0]).T\n",
+    "yt = np.array([0.0, 1.0, 1.5, 0.9, 1.0])"
    ]
   },
   {
@@ -282,7 +277,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -405,7 +400,7 @@
      "output_type": "stream",
      "text": [
       "Gpx string: Mixture[Smooth](Linear_SquaredExponentialGP(mean=LinearMean, corr=SquaredExponential, theta=[14.453108310585526], variance=441.2131727575699, likelihood=3.0317685650605943))\n",
-      "Gpx stringified JSON serialization {\"recombination\":{\"Smooth\":null},\"experts\":[{\"type\":\"GpLinearSquaredExponentialSurrogate\",\"theta\":{\"v\":1,\"dim\":[1],\"data\":[14.453108310585526]},\"likelihood\":3.0317685650605943,\"inner_params\":{\"sigma2\":441.2131727575699,\"beta\":{\"v\":1,\"dim\":[2,1],\"data\":[-0.07757161926025721,0.7944037941949736]},\"gamma\":{\"v\":1,\"dim\":[6,1],\"data\":[-0.44643167687202573,1.133131124809854,-0.3878666745284213,0.15533955394250828,-0.8959677803782301,0.4417954530263136]},\"r_chol\":{\"v\":1,\"dim\":[6,6],\"data\":[1.000000000000011,0.0,0.0,0.0,0.0,0.0,0.0001510561378024045,0.9999999885910327,0.0,0.0,0.0,0.0,1.9601672565991523e-6,0.6476128837840273,0.7619695221943696,0.0,0.0,0.0,2.434980514598138e-11,0.020037303823239316,0.21381693649172018,0.9766682262287502,0.0,0.0,3.296423703753802e-30,8.398281535208459e-13,7.44911612228923e-10,0.00001963976192234679,0.9999999998071509,0.0,4.974640459217575e-49,1.1129396734558612e-25,2.068110297817145e-21,2.386690085166188e-14,0.0048821888384808325,0.999988082045065]},\"ft\":{\"v\":1,\"dim\":[6,2],\"data\":[0.9999999999999889,-1.3292355199392736,0.9998489552694416,-0.5488312796613454,0.4625945845539201,-0.026537417389141983,0.902102824801257,-0.012517224989006932,0.9999822827627053,0.8379965520658361,0.9951297575720011,1.4407471306715083]},\"ft_qr_r\":{\"v\":1,\"dim\":[2,2],\"data\":[2.240028792174559,0.16524799061580708,0.0,2.195364975090908]}},\"w_star\":{\"v\":1,\"dim\":[1,1],\"data\":[1.0]},\"xt_norm\":{\"data\":{\"v\":1,\"dim\":[6,1],\"data\":[-1.3292355199392882,-0.549032062583619,-0.3756535165045814,-0.028896424346506258,0.8379963060486816,1.4448212173253132]},\"mean\":{\"v\":1,\"dim\":[1],\"data\":[-0.8333333333333334]},\"std\":{\"v\":1,\"dim\":[1],\"data\":[5.767726299562651]}},\"yt_norm\":{\"data\":{\"v\":1,\"dim\":[6,1],\"data\":[-1.5797826304192275,0.3712640485913234,-0.002705461006250771,0.009275082294565307,-0.3056720463069517,1.5076210068465417]},\"mean\":{\"v\":1,\"dim\":[1],\"data\":[-1.1732910418024691]},\"std\":{\"v\":1,\"dim\":[1],\"data\":[35.77542995914992]}},\"training_data\":[{\"v\":1,\"dim\":[6,1],\"data\":[-8.5,-4.0,-3.0,-1.0,4.0,7.5]},{\"v\":1,\"dim\":[6,1],\"data\":[-57.69069388704717,12.108839924926851,-1.2700800725388048,-0.8414709848078965,-12.108839924926851,52.76249869357906]}],\"params\":{\"theta_tuning\":{\"Optimized\":{\"init\":[0.01],\"bounds\":[[1e-8,100.0]]}},\"mean\":\"LinearMean\",\"corr\":\"SquaredExponential\",\"kpls_dim\":null,\"n_start\":10,\"nugget\":2.220446049250313e-14}}],\"gmx\":{\"weights\":{\"v\":1,\"dim\":[1],\"data\":[1.0]},\"means\":{\"v\":1,\"dim\":[1,1],\"data\":[-0.8333333333333334]},\"covariances\":{\"v\":1,\"dim\":[1,1,1],\"data\":[27.722223222222226]},\"precisions\":{\"v\":1,\"dim\":[1,1,1],\"data\":[0.0360721429873776]},\"precisions_chol\":{\"v\":1,\"dim\":[1,1,1],\"data\":[0.18992667792434426]},\"heaviside_factor\":1.0,\"log_det\":{\"v\":1,\"dim\":[1],\"data\":[-1.6611171869637489]}},\"gp_type\":\"FullGp\",\"training_data\":[{\"v\":1,\"dim\":[6,1],\"data\":[-8.5,-4.0,-3.0,-1.0,4.0,7.5]},{\"v\":1,\"dim\":[6,1],\"data\":[-57.69069388704717,12.108839924926851,-1.2700800725388048,-0.8414709848078965,-12.108839924926851,52.76249869357906]}],\"params\":{\"gp_type\":\"FullGp\",\"n_clusters\":1,\"recombination\":{\"Smooth\":null},\"regression_spec\":\"CONSTANT | LINEAR | QUADRATIC\",\"correlation_spec\":\"SQUAREDEXPONENTIAL | MATERN52\",\"theta_tunings\":[{\"Optimized\":{\"init\":[0.01],\"bounds\":[[1e-8,100.0]]}}],\"kpls_dim\":null,\"n_start\":10,\"gmm\":null,\"gmx\":null,\"rng\":{\"s\":[11018582338624544618,6886584510669971503,10234006225050304258,10303931937502703328]}}}\n"
+      "Gpx stringified JSON serialization {\"recombination\":{\"Smooth\":null},\"experts\":[{\"type\":\"GpLinearSquaredExponentialSurrogate\",\"theta\":{\"v\":1,\"dim\":[1],\"data\":[14.453108310585526]},\"likelihood\":3.0317685650605943,\"inner_params\":{\"sigma2\":441.2131727575699,\"beta\":{\"v\":1,\"dim\":[2,1],\"data\":[-0.07757161926025721,0.7944037941949736]},\"gamma\":{\"v\":1,\"dim\":[6,1],\"data\":[-0.44643167687202573,1.133131124809854,-0.3878666745284213,0.15533955394250828,-0.8959677803782301,0.4417954530263136]},\"r_chol\":{\"v\":1,\"dim\":[6,6],\"data\":[1.000000000000011,0.0,0.0,0.0,0.0,0.0,0.0001510561378024045,0.9999999885910327,0.0,0.0,0.0,0.0,1.9601672565991523e-6,0.6476128837840273,0.7619695221943696,0.0,0.0,0.0,2.434980514598138e-11,0.020037303823239316,0.21381693649172018,0.9766682262287502,0.0,0.0,3.296423703753802e-30,8.398281535208459e-13,7.44911612228923e-10,0.00001963976192234679,0.9999999998071509,0.0,4.974640459217575e-49,1.1129396734558612e-25,2.068110297817145e-21,2.386690085166188e-14,0.0048821888384808325,0.999988082045065]},\"ft\":{\"v\":1,\"dim\":[6,2],\"data\":[0.9999999999999889,-1.3292355199392736,0.9998489552694416,-0.5488312796613454,0.4625945845539201,-0.026537417389141983,0.902102824801257,-0.012517224989006932,0.9999822827627053,0.8379965520658361,0.9951297575720011,1.4407471306715083]},\"ft_qr_r\":{\"v\":1,\"dim\":[2,2],\"data\":[2.240028792174559,0.16524799061580708,0.0,2.195364975090908]}},\"w_star\":{\"v\":1,\"dim\":[1,1],\"data\":[1.0]},\"xt_norm\":{\"data\":{\"v\":1,\"dim\":[6,1],\"data\":[-1.3292355199392882,-0.549032062583619,-0.3756535165045814,-0.028896424346506258,0.8379963060486816,1.4448212173253132]},\"mean\":{\"v\":1,\"dim\":[1],\"data\":[-0.8333333333333334]},\"std\":{\"v\":1,\"dim\":[1],\"data\":[5.767726299562651]}},\"yt_norm\":{\"data\":{\"v\":1,\"dim\":[6,1],\"data\":[-1.5797826304192275,0.3712640485913234,-0.002705461006250771,0.009275082294565307,-0.3056720463069517,1.5076210068465417]},\"mean\":{\"v\":1,\"dim\":[1],\"data\":[-1.1732910418024691]},\"std\":{\"v\":1,\"dim\":[1],\"data\":[35.77542995914992]}},\"training_data\":[{\"v\":1,\"dim\":[6,1],\"data\":[-8.5,-4.0,-3.0,-1.0,4.0,7.5]},{\"v\":1,\"dim\":[6],\"data\":[-57.69069388704717,12.108839924926851,-1.2700800725388048,-0.8414709848078965,-12.108839924926851,52.76249869357906]}],\"params\":{\"theta_tuning\":{\"Optimized\":{\"init\":[0.01],\"bounds\":[[1e-8,100.0]]}},\"mean\":\"LinearMean\",\"corr\":\"SquaredExponential\",\"kpls_dim\":null,\"n_start\":10,\"nugget\":2.220446049250313e-14}}],\"gmx\":{\"weights\":{\"v\":1,\"dim\":[1],\"data\":[1.0]},\"means\":{\"v\":1,\"dim\":[1,1],\"data\":[-0.8333333333333334]},\"covariances\":{\"v\":1,\"dim\":[1,1,1],\"data\":[27.722223222222226]},\"precisions\":{\"v\":1,\"dim\":[1,1,1],\"data\":[0.0360721429873776]},\"precisions_chol\":{\"v\":1,\"dim\":[1,1,1],\"data\":[0.18992667792434426]},\"heaviside_factor\":1.0,\"log_det\":{\"v\":1,\"dim\":[1],\"data\":[-1.6611171869637489]}},\"gp_type\":\"FullGp\",\"training_data\":[{\"v\":1,\"dim\":[6,1],\"data\":[-8.5,-4.0,-3.0,-1.0,4.0,7.5]},{\"v\":1,\"dim\":[6],\"data\":[-57.69069388704717,12.108839924926851,-1.2700800725388048,-0.8414709848078965,-12.108839924926851,52.76249869357906]}],\"params\":{\"gp_type\":\"FullGp\",\"n_clusters\":1,\"recombination\":{\"Smooth\":null},\"regression_spec\":\"CONSTANT | LINEAR | QUADRATIC\",\"correlation_spec\":\"SQUAREDEXPONENTIAL | MATERN52\",\"theta_tunings\":[{\"Optimized\":{\"init\":[0.01],\"bounds\":[[1e-8,100.0]]}}],\"kpls_dim\":null,\"n_start\":10,\"gmm\":null,\"gmx\":null,\"rng\":{\"s\":[10217383296741244220,3907610133719294665,10702447564111669569,12760811216116011873]}}}\n"
      ]
     }
    ],
@@ -570,7 +565,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -684,7 +679,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Mixture[Smooth(0.1)](Constant_SquaredExponentialGP(mean=ConstantMean, corr=SquaredExponential, theta=[0.030558468159793944], variance=0.9805836846291843, likelihood=89.03681533053401), Constant_SquaredExponentialGP(mean=ConstantMean, corr=SquaredExponential, theta=[0.027856606714033984], variance=0.026494441460099966, likelihood=278.25736821645546), Constant_SquaredExponentialGP(mean=ConstantMean, corr=SquaredExponential, theta=[0.007858695608853907], variance=1.4186216960244649, likelihood=192.5430848398401))\n"
+      "Mixture[Smooth(0.1)](Constant_SquaredExponentialGP(mean=ConstantMean, corr=SquaredExponential, theta=[0.027856606714033984], variance=0.026494441460099966, likelihood=278.25736821645546), Constant_SquaredExponentialGP(mean=ConstantMean, corr=SquaredExponential, theta=[0.007858695608853907], variance=1.4186216960244649, likelihood=192.5430848398401), Constant_SquaredExponentialGP(mean=ConstantMean, corr=SquaredExponential, theta=[0.030558468159793944], variance=0.9805836846291843, likelihood=89.03681533053401))\n"
      ]
     }
    ],
@@ -801,18 +796,26 @@
    "metadata": {},
    "outputs": [
     {
-     "ename": "PanicException",
-     "evalue": "index out of bounds: the len is 0 but the index is 0",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[1;31mPanicException\u001b[0m                            Traceback (most recent call last)",
-      "Cell \u001b[1;32mIn[26], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m gpx \u001b[38;5;241m=\u001b[39m \u001b[43megx\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mGpx\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbuilder\u001b[49m\u001b[43m(\u001b[49m\u001b[43mn_clusters\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mxt\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43myt\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m      2\u001b[0m \u001b[38;5;28mprint\u001b[39m(gpx)\n\u001b[0;32m      3\u001b[0m y \u001b[38;5;241m=\u001b[39m gpx\u001b[38;5;241m.\u001b[39mpredict(x)\n",
-      "\u001b[1;31mPanicException\u001b[0m: index out of bounds: the len is 0 but the index is 0"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(60, 1)\n",
+      "Mixture[Hard](Constant_SquaredExponentialGP(mean=ConstantMean, corr=SquaredExponential, theta=[0.027856606714033984], variance=0.026494441460099966, likelihood=278.25736821645546), Constant_SquaredExponentialGP(mean=ConstantMean, corr=SquaredExponential, theta=[0.007858695608853907], variance=1.4186216960244649, likelihood=192.5430848398401), Constant_SquaredExponentialGP(mean=ConstantMean, corr=SquaredExponential, theta=[0.030558468159793944], variance=0.9805836846291843, likelihood=89.03681533053401))\n"
      ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
     }
    ],
    "source": [
+    "print(yt.shape)\n",
     "gpx = egx.Gpx.builder(n_clusters=0).fit(xt, yt)\n",
     "print(gpx)\n",
     "y = gpx.predict(x)\n",
@@ -831,7 +834,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 27,
    "id": "c3db4c30",
    "metadata": {},
    "outputs": [
@@ -863,7 +866,7 @@
       " |      CorrelationSpec.MATERN32 (4), CorrelationSpec.MATERN52 (8) or\n",
       " |      any bit-wise union of these values (e.g. CorrelationSpec.MATERN32 | CorrelationSpec.MATERN52)\n",
       " |  \n",
-      " |  recombination (Recombination.Smooth or Recombination.Hard)\n",
+      " |  recombination (Recombination.Smooth or Recombination.Hard (default))\n",
       " |      Specify how the various experts predictions are recombined\n",
       " |      * Smooth: prediction is a combination of experts prediction wrt their responsabilities,\n",
       " |      the heaviside factor which controls steepness of the change between experts regions is optimized\n",
@@ -916,7 +919,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 28,
    "id": "284f975e",
    "metadata": {},
    "outputs": [
@@ -937,6 +940,12 @@
       " |  __str__(self, /)\n",
       " |      Return str(self).\n",
       " |  \n",
+      " |  dims(self, /)\n",
+      " |      Get the input and output dimensions of the surrogate\n",
+      " |      \n",
+      " |      Returns\n",
+      " |          the couple (nx, ny)\n",
+      " |  \n",
       " |  likelihoods(self, /)\n",
       " |      Get reduced likelihood values gotten when fitting the GP experts\n",
       " |      \n",
@@ -999,11 +1008,15 @@
       " |          the trajectories as an array[nsamples, n_traj]\n",
       " |  \n",
       " |  save(self, /, filename)\n",
-      " |      Save Gaussian processes mixture in a json file.\n",
+      " |      Save Gaussian processes mixture in a file.\n",
+      " |      If the filename has .json JSON human readable format is used\n",
+      " |      otherwise an optimized binary format is used.\n",
       " |      \n",
       " |      Parameters\n",
-      " |          filename (string)\n",
-      " |              json file generated in the current directory\n",
+      " |          filename with .json or .bin extension (string)\n",
+      " |              file generated in the current directory\n",
+      " |      \n",
+      " |      Returns True if save succeeds otherwise False\n",
       " |  \n",
       " |  thetas(self, /)\n",
       " |      Get optimized thetas hyperparameters (ie once GP experts are fitted)\n",
@@ -1011,6 +1024,12 @@
       " |      Returns\n",
       " |          thetas as an array[n_clusters, nx or kpls_dim]\n",
       " |  \n",
+      " |  training_data(self, /)\n",
+      " |      Get the nt training data points used to fit the surrogate\n",
+      " |      \n",
+      " |      Returns\n",
+      " |          the couple (ndarray[nt, nx], ndarray[nt,])\n",
+      " |  \n",
       " |  variances(self, /)\n",
       " |      Get GP expert variance (ie posterior GP variance)\n",
       " |      \n",
@@ -1029,7 +1048,7 @@
       " |      See `GpMix` constructor\n",
       " |  \n",
       " |  load(filename)\n",
-      " |      Load Gaussian processes mixture from a json file.\n",
+      " |      Load Gaussian processes mixture from file.\n",
       " |      \n",
       " |      Parameters\n",
       " |          filename (string)\n",
diff --git a/ego/src/criteria/ei.rs b/ego/src/criteria/ei.rs
index 9cdf2e86..ed79d53e 100644
--- a/ego/src/criteria/ei.rs
+++ b/ego/src/criteria/ei.rs
@@ -28,7 +28,7 @@ impl InfillCriterion for ExpectedImprovement {
         let pt = ArrayView::from_shape((1, x.len()), x).unwrap();
         if let Ok(p) = obj_model.predict(&pt) {
             if let Ok(s) = obj_model.predict_var(&pt) {
-                let pred = p[[0, 0]];
+                let pred = p[0];
                 let sigma = s[[0, 0]].sqrt();
                 let args0 = (fmin - pred) / sigma;
                 let args1 = (fmin - pred) * norm_cdf(args0);
@@ -58,7 +58,7 @@ impl InfillCriterion for ExpectedImprovement {
                 if sigma.abs() < 1e-12 {
                     Array1::zeros(pt.len())
                 } else {
-                    let pred = p[[0, 0]];
+                    let pred = p[0];
                     let diff_y = fmin - pred;
                     let arg = (fmin - pred) / sigma;
                     let y_prime = obj_model.predict_gradients(&pt).unwrap();
diff --git a/ego/src/criteria/wb2.rs b/ego/src/criteria/wb2.rs
index 9342f7eb..bb545da4 100644
--- a/ego/src/criteria/wb2.rs
+++ b/ego/src/criteria/wb2.rs
@@ -31,7 +31,7 @@ impl InfillCriterion for WB2Criterion {
         let scale = scale.unwrap_or(self.0.unwrap_or(1.0));
         let pt = ArrayView::from_shape((1, x.len()), x).unwrap();
         let ei = EI.value(x, obj_model, fmin, None);
-        scale * ei - obj_model.predict(&pt).unwrap()[[0, 0]]
+        scale * ei - obj_model.predict(&pt).unwrap()[0]
     }
 
     /// Computes derivatives of WB2S infill criterion wrt to x components at given `x` point
@@ -78,7 +78,7 @@ pub(crate) fn compute_wb2s_scale(
     let i_max = ei_x.argmax().unwrap();
     let pred_max = obj_model
         .predict(&x.row(i_max).insert_axis(Axis(0)))
-        .unwrap()[[0, 0]];
+        .unwrap()[0];
     let ei_max = ei_x[i_max];
     if ei_max.abs() > 100. * f64::EPSILON {
         ratio * pred_max / ei_max
@@ -113,7 +113,7 @@ mod tests {
             .regression_spec(RegressionSpec::CONSTANT)
             .correlation_spec(CorrelationSpec::SQUAREDEXPONENTIAL)
             .recombination(Recombination::Hard)
-            .fit(&Dataset::new(xt, yt))
+            .fit(&Dataset::new(xt, yt.remove_axis(Axis(1))))
             .expect("GP fitting");
         let bgp = Box::new(gp) as Box<dyn MixtureGpSurrogate>;
 
@@ -153,12 +153,7 @@ mod tests {
         let fdiff2 = (bgp.predict(&xtest21.view()).unwrap()
             - bgp.predict(&xtest22.view()).unwrap())
             / (2. * h);
-        println!(
-            "gp fdiff({}) = [[{}, {}]]",
-            xtest,
-            fdiff1[[0, 0]],
-            fdiff2[[0, 0]]
-        );
+        println!("gp fdiff({}) = [[{}, {}]]", xtest, fdiff1[0], fdiff2[0]);
         println!(
             "GP predict derivatives({}) = {}",
             xtest,
diff --git a/ego/src/gpmix/mixint.rs b/ego/src/gpmix/mixint.rs
index 7361cfbd..305537ca 100644
--- a/ego/src/gpmix/mixint.rs
+++ b/ego/src/gpmix/mixint.rs
@@ -14,7 +14,9 @@ use egobox_moe::{
 };
 use linfa::traits::{Fit, PredictInplace};
 use linfa::{DatasetBase, Float, ParamGuard};
-use ndarray::{s, Array, Array2, ArrayBase, ArrayView2, Axis, Data, DataMut, Ix2, Zip};
+use ndarray::{
+    s, Array, Array1, Array2, ArrayBase, ArrayView1, ArrayView2, Axis, Data, DataMut, Ix1, Ix2, Zip,
+};
 use ndarray_rand::rand::SeedableRng;
 use ndarray_stats::QuantileExt;
 use rand_xoshiro::Xoshiro256Plus;
@@ -343,7 +345,7 @@ impl MixintGpMixtureValidParams {
     fn _train(
         &self,
         xt: &ArrayBase<impl Data<Elem = f64>, Ix2>,
-        yt: &ArrayBase<impl Data<Elem = f64>, Ix2>,
+        yt: &ArrayBase<impl Data<Elem = f64>, Ix1>,
     ) -> Result<MixintGpMixture> {
         let mut xcast = if self.work_in_folded_space {
             unfold_with_enum_mask(&self.xtypes, &xt.view())
@@ -369,7 +371,7 @@ impl MixintGpMixtureValidParams {
     fn _train_on_clusters(
         &self,
         xt: &ArrayBase<impl Data<Elem = f64>, Ix2>,
-        yt: &ArrayBase<impl Data<Elem = f64>, Ix2>,
+        yt: &ArrayBase<impl Data<Elem = f64>, Ix1>,
         clustering: &egobox_moe::Clustering,
     ) -> Result<MixintGpMixture> {
         let mut xcast = if self.work_in_folded_space {
@@ -458,32 +460,32 @@ impl SurrogateBuilder for MixintGpMixtureParams {
 
     fn train(
         &self,
-        xt: &ArrayView2<f64>,
-        yt: &ArrayView2<f64>,
+        xt: ArrayView2<f64>,
+        yt: ArrayView1<f64>,
     ) -> Result<Box<dyn MixtureGpSurrogate>> {
-        let mixmoe = self.check_ref()?._train(xt, yt)?;
+        let mixmoe = self.check_ref()?._train(&xt, &yt)?;
         Ok(mixmoe).map(|mixmoe| Box::new(mixmoe) as Box<dyn MixtureGpSurrogate>)
     }
 
     fn train_on_clusters(
         &self,
-        xt: &ArrayView2<f64>,
-        yt: &ArrayView2<f64>,
+        xt: ArrayView2<f64>,
+        yt: ArrayView1<f64>,
         clustering: &Clustering,
     ) -> Result<Box<dyn MixtureGpSurrogate>> {
-        let mixmoe = self.check_ref()?._train_on_clusters(xt, yt, clustering)?;
+        let mixmoe = self.check_ref()?._train_on_clusters(&xt, &yt, clustering)?;
         Ok(mixmoe).map(|mixmoe| Box::new(mixmoe) as Box<dyn MixtureGpSurrogate>)
     }
 }
 
-impl<D: Data<Elem = f64>> Fit<ArrayBase<D, Ix2>, ArrayBase<D, Ix2>, EgoError>
+impl<D: Data<Elem = f64>> Fit<ArrayBase<D, Ix2>, ArrayBase<D, Ix1>, EgoError>
     for MixintGpMixtureValidParams
 {
     type Object = MixintGpMixture;
 
     fn fit(
         &self,
-        dataset: &DatasetBase<ArrayBase<D, Ix2>, ArrayBase<D, Ix2>>,
+        dataset: &DatasetBase<ArrayBase<D, Ix2>, ArrayBase<D, Ix1>>,
     ) -> Result<Self::Object> {
         let x = dataset.records();
         let y = dataset.targets();
@@ -522,7 +524,7 @@ pub struct MixintGpMixture {
     /// i.e for "blue" in ["red", "green", "blue"] either \[2\] or [0, 0, 1]
     work_in_folded_space: bool,
     /// Training inputs
-    training_data: (Array2<f64>, Array2<f64>),
+    training_data: (Array2<f64>, Array1<f64>),
     /// Parameters used to trin this model
     params: MixintGpMixtureValidParams,
 }
@@ -559,7 +561,7 @@ impl GpSurrogate for MixintGpMixture {
         self.moe.dims()
     }
 
-    fn predict(&self, x: &ArrayView2<f64>) -> egobox_moe::Result<Array2<f64>> {
+    fn predict(&self, x: &ArrayView2<f64>) -> egobox_moe::Result<Array1<f64>> {
         let mut xcast = if self.work_in_folded_space {
             unfold_with_enum_mask(&self.xtypes, x)
         } else {
@@ -628,7 +630,7 @@ impl GpSurrogateExt for MixintGpMixture {
 }
 
 impl CrossValScore<f64, EgoError, MixintGpMixtureParams, Self> for MixintGpMixture {
-    fn training_data(&self) -> &(Array2<f64>, Array2<f64>) {
+    fn training_data(&self) -> &(Array2<f64>, Array1<f64>) {
         &self.training_data
     }
 
@@ -643,11 +645,11 @@ impl MixtureGpSurrogate for MixintGpMixture {
     }
 }
 
-impl<D: Data<Elem = f64>> PredictInplace<ArrayBase<D, Ix2>, Array2<f64>> for MixintGpMixture {
-    fn predict_inplace(&self, x: &ArrayBase<D, Ix2>, y: &mut Array2<f64>) {
+impl<D: Data<Elem = f64>> PredictInplace<ArrayBase<D, Ix2>, Array1<f64>> for MixintGpMixture {
+    fn predict_inplace(&self, x: &ArrayBase<D, Ix2>, y: &mut Array1<f64>) {
         assert_eq!(
             x.nrows(),
-            y.nrows(),
+            y.len(),
             "The number of data points must match the number of output targets."
         );
 
@@ -655,8 +657,8 @@ impl<D: Data<Elem = f64>> PredictInplace<ArrayBase<D, Ix2>, Array2<f64>> for Mix
         *y = values;
     }
 
-    fn default_target(&self, x: &ArrayBase<D, Ix2>) -> Array2<f64> {
-        Array2::zeros((x.nrows(), self.moe.dims().1))
+    fn default_target(&self, x: &ArrayBase<D, Ix2>) -> Array1<f64> {
+        Array1::zeros((x.nrows(),))
     }
 }
 
@@ -760,7 +762,7 @@ impl MixintContext {
     pub fn create_surrogate(
         &self,
         surrogate_builder: &MoeBuilder,
-        dataset: &DatasetBase<Array2<f64>, Array2<f64>>,
+        dataset: &DatasetBase<Array2<f64>, Array1<f64>>,
     ) -> Result<MixintGpMixture> {
         let mut params = MixintGpMixtureParams::new(&self.xtypes, surrogate_builder);
         let params = params.work_in_folded_space(self.work_in_folded_space);
@@ -870,7 +872,7 @@ mod tests {
 
         let surrogate_builder = MoeBuilder::new();
         let xt = array![[0.], [2.], [3.0], [4.]];
-        let yt = array![[0.], [1.5], [0.9], [1.]];
+        let yt = array![0., 1.5, 0.9, 1.];
         let ds = Dataset::new(xt, yt);
         let mixi_moe = mixi
             .create_surrogate(&surrogate_builder, &ds)
@@ -884,7 +886,7 @@ mod tests {
             .expect("Predict var fail");
         println!("{ytest:?}");
         assert_abs_diff_eq!(
-            array![[0.], [0.7872696212255119], [1.5], [0.9], [1.]],
+            array![0., 0.7872696212255119, 1.5, 0.9, 1.],
             ytest,
             epsilon = 1e-3
         );
@@ -894,13 +896,13 @@ mod tests {
             yvar,
             epsilon = 1e-3
         );
-        println!("LOOCV = {}", mixi_moe.loocv_score());
+        //println!("LOOCV = {}", mixi_moe.loocv_score());
     }
 
-    fn ftest(x: &Array2<f64>) -> Array2<f64> {
-        let mut y = (x.column(0).to_owned() * x.column(0)).insert_axis(Axis(1));
-        y = &y + (x.column(1).to_owned() * x.column(1)).insert_axis(Axis(1));
-        y = &y * (x.column(2).insert_axis(Axis(1)).mapv(|v| v + 1.));
+    fn ftest(x: &Array2<f64>) -> Array1<f64> {
+        let mut y = x.column(0).to_owned() * x.column(0);
+        y = &y + (x.column(1).to_owned() * x.column(1));
+        y = &y * (x.column(2).mapv(|v| v + 1.));
         y
     }
 
diff --git a/ego/src/gpmix/mod.rs b/ego/src/gpmix/mod.rs
index eea08148..4f608152 100644
--- a/ego/src/gpmix/mod.rs
+++ b/ego/src/gpmix/mod.rs
@@ -7,7 +7,7 @@ use egobox_gp::ThetaTuning;
 use egobox_moe::{
     Clustering, CorrelationSpec, GpMixtureParams, MixtureGpSurrogate, RegressionSpec,
 };
-use ndarray::ArrayView2;
+use ndarray::{ArrayView1, ArrayView2};
 
 use linfa::ParamGuard;
 
@@ -51,22 +51,22 @@ impl SurrogateBuilder for GpMixtureParams<f64> {
 
     fn train(
         &self,
-        xt: &ArrayView2<f64>,
-        yt: &ArrayView2<f64>,
+        xt: ArrayView2<f64>,
+        yt: ArrayView1<f64>,
     ) -> Result<Box<dyn MixtureGpSurrogate>> {
         let checked = self.check_ref()?;
-        let moe = checked.train(xt, yt)?;
+        let moe = checked.train(&xt, &yt)?;
         Ok(moe).map(|moe| Box::new(moe) as Box<dyn MixtureGpSurrogate>)
     }
 
     fn train_on_clusters(
         &self,
-        xt: &ArrayView2<f64>,
-        yt: &ArrayView2<f64>,
+        xt: ArrayView2<f64>,
+        yt: ArrayView1<f64>,
         clustering: &Clustering,
     ) -> Result<Box<dyn MixtureGpSurrogate>> {
         let checked = self.check_ref()?;
-        let moe = checked.train_on_clusters(xt, yt, clustering)?;
+        let moe = checked.train_on_clusters(&xt, &yt, clustering)?;
         Ok(moe).map(|moe| Box::new(moe) as Box<dyn MixtureGpSurrogate>)
     }
 }
diff --git a/ego/src/solver/egor_impl.rs b/ego/src/solver/egor_impl.rs
index 9c1b043b..981bd5a5 100644
--- a/ego/src/solver/egor_impl.rs
+++ b/ego/src/solver/egor_impl.rs
@@ -97,7 +97,7 @@ where
         &self,
         model_name: &str,
         xt: &ArrayBase<impl Data<Elem = f64>, Ix2>,
-        yt: &ArrayBase<impl Data<Elem = f64>, Ix2>,
+        yt: &ArrayBase<impl Data<Elem = f64>, Ix1>,
         make_clustering: bool,
         optimize_theta: bool,
         clustering: Option<&Clustering>,
@@ -114,7 +114,7 @@ where
         {
             info!("{} Clustering and training...", model_name);
             let model = builder
-                .train(&xt.view(), &yt.view())
+                .train(xt.view(), yt.view())
                 .expect("GP training failure");
             info!(
                 "... {} trained ({} / {})",
@@ -155,7 +155,7 @@ where
             builder.set_theta_tunings(&theta_tunings);
 
             let model = builder
-                .train_on_clusters(&xt.view(), &yt.view(), clustering)
+                .train_on_clusters(xt.view(), yt.view(), clustering)
                 .expect("GP training failure");
             model
         }
@@ -204,13 +204,7 @@ where
                 self.make_clustered_surrogate(
                     &name,
                     &state.data.as_ref().unwrap().0,
-                    &state
-                        .data
-                        .as_ref()
-                        .unwrap()
-                        .1
-                        .slice(s![.., k..k + 1])
-                        .to_owned(),
+                    &state.data.as_ref().unwrap().1.slice(s![.., k]).to_owned(),
                     false,
                     true,
                     state.clusterings.as_ref().unwrap()[k].as_ref(),
@@ -412,7 +406,7 @@ where
                     self.make_clustered_surrogate(
                         &name,
                         &xt,
-                        &yt.slice(s![.., k..k + 1]).to_owned(),
+                        &yt.slice(s![.., k]).to_owned(),
                         make_clustering,
                         optimize_theta,
                         clusterings[k].as_ref(),
@@ -595,7 +589,7 @@ where
                                 .unwrap()
                                 .view(),
                         )
-                        .unwrap()[[0, 0]]
+                        .unwrap()[0]
                         / scale_cstr
                 };
                 #[cfg(feature = "nlopt")]
@@ -684,7 +678,7 @@ where
             Ok(res)
         } else {
             let x = &xk.view().insert_axis(Axis(0));
-            let pred = obj_model.predict(x)?[[0, 0]];
+            let pred = obj_model.predict(x)?[0];
             let var = obj_model.predict_var(x)?[[0, 0]];
             let conf = match self.config.q_ei {
                 QEiStrategy::KrigingBeliever => 0.,
@@ -694,7 +688,7 @@ where
             };
             res.push(pred + conf * f64::sqrt(var));
             for cstr_model in cstr_models {
-                res.push(cstr_model.predict(x)?[[0, 0]]);
+                res.push(cstr_model.predict(x)?[0]);
             }
             Ok(res)
         }
diff --git a/ego/src/solver/trego.rs b/ego/src/solver/trego.rs
index caa9fd8c..0a2911c9 100644
--- a/ego/src/solver/trego.rs
+++ b/ego/src/solver/trego.rs
@@ -156,7 +156,7 @@ impl<SB: SurrogateBuilder + DeserializeOwned> EgorSolver<SB> {
                                 .unwrap()
                                 .view(),
                         )
-                        .unwrap()[[0, 0]]
+                        .unwrap()[0]
                         / scale_cstr
                 };
                 #[cfg(feature = "nlopt")]
diff --git a/ego/src/types.rs b/ego/src/types.rs
index d20b895f..e1620546 100644
--- a/ego/src/types.rs
+++ b/ego/src/types.rs
@@ -3,7 +3,7 @@ use crate::{errors::Result, EgorState};
 use argmin::core::CostFunction;
 use egobox_moe::{Clustering, MixtureGpSurrogate, ThetaTuning};
 use linfa::Float;
-use ndarray::{Array1, Array2, ArrayView2};
+use ndarray::{Array1, Array2, ArrayView1, ArrayView2};
 use serde::{Deserialize, Serialize};
 
 /// Optimization result
@@ -129,15 +129,15 @@ pub trait SurrogateBuilder: Clone + Serialize + Sync {
     /// Train the surrogate with given training dataset (x, y)
     fn train(
         &self,
-        xt: &ArrayView2<f64>,
-        yt: &ArrayView2<f64>,
+        xt: ArrayView2<f64>,
+        yt: ArrayView1<f64>,
     ) -> Result<Box<dyn MixtureGpSurrogate>>;
 
     /// Train the surrogate with given training dataset (x, y) and given clustering
     fn train_on_clusters(
         &self,
-        xt: &ArrayView2<f64>,
-        yt: &ArrayView2<f64>,
+        xt: ArrayView2<f64>,
+        yt: ArrayView1<f64>,
         clustering: &Clustering,
     ) -> Result<Box<dyn MixtureGpSurrogate>>;
 }
diff --git a/gp/benches/gp.rs b/gp/benches/gp.rs
index 65529ad0..ac5d1c0b 100644
--- a/gp/benches/gp.rs
+++ b/gp/benches/gp.rs
@@ -40,11 +40,10 @@ fn criterion_gp(c: &mut Criterion) {
         let yt = match read_npy(&yfilename) {
             Ok(yt) => yt,
             Err(_) => {
-                let mut yv: Array1<f64> = Array1::zeros(xt.nrows());
-                Zip::from(&mut yv).and(xt.rows()).par_for_each(|y, x| {
+                let mut yt: Array1<f64> = Array1::zeros(xt.nrows());
+                Zip::from(&mut yt).and(xt.rows()).par_for_each(|y, x| {
                     *y = griewank(&x.to_owned());
                 });
-                let yt = yv.into_shape((xt.nrows(), 1)).unwrap();
                 write_npy(&yfilename, &yt).expect("cannot save yt");
                 yt
             }
diff --git a/gp/examples/kriging.rs b/gp/examples/kriging.rs
index 65e11d74..e8700b31 100644
--- a/gp/examples/kriging.rs
+++ b/gp/examples/kriging.rs
@@ -1,9 +1,9 @@
 use egobox_gp::{correlation_models::*, mean_models::*, GaussianProcess};
 use linfa::prelude::*;
-use ndarray::{arr2, concatenate, Array, Array2, Axis};
+use ndarray::{arr2, concatenate, Array, Array1, Array2, Axis};
 
-fn xsinx(x: &Array2<f64>) -> Array2<f64> {
-    (x - 3.5) * ((x - 3.5) / std::f64::consts::PI).mapv(|v| v.sin())
+fn xsinx(x: &Array2<f64>) -> Array1<f64> {
+    ((x - 3.5) * ((x - 3.5) / std::f64::consts::PI).mapv(|v| v.sin())).remove_axis(Axis(1))
 }
 
 fn main() {
@@ -29,5 +29,8 @@ fn main() {
         .map(|v| v.sqrt());
 
     println!("Compute prediction errors (x, err(x))");
-    println!("{}", concatenate![Axis(1), xtest, (ypred - ytest), ysigma]);
+    println!(
+        "{}",
+        concatenate![Axis(1), xtest, (ypred - ytest).insert_axis(Axis(1)), ysigma]
+    );
 }
diff --git a/gp/src/algorithm.rs b/gp/src/algorithm.rs
index c93dfd19..991b8d14 100644
--- a/gp/src/algorithm.rs
+++ b/gp/src/algorithm.rs
@@ -116,11 +116,11 @@ impl<F: Float> Clone for GpInnerParams<F> {
 /// ```no_run
 /// use egobox_gp::{correlation_models::*, mean_models::*, GaussianProcess};
 /// use linfa::prelude::*;
-/// use ndarray::{arr2, concatenate, Array, Array2, Axis};
+/// use ndarray::{arr2, concatenate, Array, Array1, Array2, Axis};
 ///
 /// // one-dimensional test function to approximate
-/// fn xsinx(x: &Array2<f64>) -> Array2<f64> {
-///     (x - 3.5) * ((x - 3.5) / std::f64::consts::PI).mapv(|v| v.sin())
+/// fn xsinx(x: &Array2<f64>) -> Array1<f64> {
+///     ((x - 3.5) * ((x - 3.5) / std::f64::consts::PI).mapv(|v| v.sin())).remove_axis(Axis(1))
 /// }
 ///
 /// // training data
@@ -177,7 +177,7 @@ pub struct GaussianProcess<F: Float, Mean: RegressionModel<F>, Corr: Correlation
     /// Training outputs
     yt_norm: NormalizedData<F>,
     /// Training dataset (input, output)
-    pub(crate) training_data: (Array2<F>, Array2<F>),
+    pub(crate) training_data: (Array2<F>, Array1<F>),
     /// Parameters used to fit this model
     pub(crate) params: GpValidParams<F, Mean, Corr>,
 }
@@ -239,8 +239,8 @@ impl<F: Float, Mean: RegressionModel<F>, Corr: CorrelationModel<F>> GaussianProc
     }
 
     /// Predict output values at n given `x` points of nx components specified as a (n, nx) matrix.
-    /// Returns n scalar output values as (n, 1) column vector.
-    pub fn predict(&self, x: &ArrayBase<impl Data<Elem = F>, Ix2>) -> Result<Array2<F>> {
+    /// Returns n scalar output values as a vector (n,).
+    pub fn predict(&self, x: &ArrayBase<impl Data<Elem = F>, Ix2>) -> Result<Array1<F>> {
         let xnorm = (x - &self.xt_norm.mean) / &self.xt_norm.std;
         // Compute the mean term at x
         let f = self.params.mean.value(&xnorm);
@@ -249,7 +249,7 @@ impl<F: Float, Mean: RegressionModel<F>, Corr: CorrelationModel<F>> GaussianProc
         // Scaled predictor
         let y_ = &f.dot(&self.inner_params.beta) + &corr.dot(&self.inner_params.gamma);
         // Predictor
-        Ok(&y_ * &self.yt_norm.std + &self.yt_norm.mean)
+        Ok((&y_ * &self.yt_norm.std + &self.yt_norm.mean).remove_axis(Axis(1)))
     }
 
     /// Predict variance values at n given `x` points of nx components specified as a (n, nx) matrix.
@@ -364,7 +364,7 @@ impl<F: Float, Mean: RegressionModel<F>, Corr: CorrelationModel<F>> GaussianProc
     ) -> Array2<F> {
         let mean = self.predict(x).unwrap();
         let cov = self._compute_covariance(x);
-        sample(x, mean, cov, n_traj, method)
+        sample(x, mean.insert_axis(Axis(1)), cov, n_traj, method)
     }
 
     /// Retrieve optimized hyperparameters theta
@@ -666,7 +666,7 @@ impl<F: Float, Mean: RegressionModel<F>, Corr: CorrelationModel<F>> GaussianProc
     }
 }
 
-impl<F, D, Mean, Corr> PredictInplace<ArrayBase<D, Ix2>, Array2<F>>
+impl<F, D, Mean, Corr> PredictInplace<ArrayBase<D, Ix2>, Array1<F>>
     for GaussianProcess<F, Mean, Corr>
 where
     F: Float,
@@ -674,10 +674,10 @@ where
     Mean: RegressionModel<F>,
     Corr: CorrelationModel<F>,
 {
-    fn predict_inplace(&self, x: &ArrayBase<D, Ix2>, y: &mut Array2<F>) {
+    fn predict_inplace(&self, x: &ArrayBase<D, Ix2>, y: &mut Array1<F>) {
         assert_eq!(
             x.nrows(),
-            y.nrows(),
+            y.len(),
             "The number of data points must match the number of output targets."
         );
 
@@ -685,8 +685,8 @@ where
         *y = values;
     }
 
-    fn default_target(&self, x: &ArrayBase<D, Ix2>) -> Array2<F> {
-        Array2::zeros((x.nrows(), self.dims().1))
+    fn default_target(&self, x: &ArrayBase<D, Ix2>) -> Array1<F> {
+        Array1::zeros((x.nrows(),))
     }
 }
 
@@ -723,23 +723,18 @@ where
 }
 
 impl<F: Float, Mean: RegressionModel<F>, Corr: CorrelationModel<F>, D: Data<Elem = F>>
-    Fit<ArrayBase<D, Ix2>, ArrayBase<D, Ix2>, GpError> for GpValidParams<F, Mean, Corr>
+    Fit<ArrayBase<D, Ix2>, ArrayBase<D, Ix1>, GpError> for GpValidParams<F, Mean, Corr>
 {
     type Object = GaussianProcess<F, Mean, Corr>;
 
     /// Fit GP parameters using maximum likelihood
     fn fit(
         &self,
-        dataset: &DatasetBase<ArrayBase<D, Ix2>, ArrayBase<D, Ix2>>,
+        dataset: &DatasetBase<ArrayBase<D, Ix2>, ArrayBase<D, Ix1>>,
     ) -> Result<Self::Object> {
         let x = dataset.records();
-        let y = dataset.targets();
-        if y.ncols() > 1 {
-            panic!(
-                "Multiple outputs not handled, a one-dimensional column vector \
-            as training output data is expected"
-            );
-        }
+        let y = dataset.targets().to_owned().insert_axis(Axis(1));
+
         if let Some(d) = self.kpls_dim() {
             if *d > x.ncols() {
                 return Err(GpError::InvalidValueError(format!(
@@ -752,7 +747,7 @@ impl<F: Float, Mean: RegressionModel<F>, Corr: CorrelationModel<F>, D: Data<Elem
         }
 
         let xtrain = NormalizedData::new(x);
-        let ytrain = NormalizedData::new(y);
+        let ytrain = NormalizedData::new(&y);
 
         let mut w_star = Array2::eye(x.ncols());
         if let Some(n_components) = self.kpls_dim() {
@@ -871,7 +866,7 @@ impl<F: Float, Mean: RegressionModel<F>, Corr: CorrelationModel<F>, D: Data<Elem
             w_star,
             xt_norm: xtrain,
             yt_norm: ytrain,
-            training_data: (x.to_owned(), y.to_owned()),
+            training_data: (x.to_owned(), y.to_owned().remove_axis(Axis(1))),
             params: self.clone(),
         })
     }
@@ -1100,7 +1095,7 @@ mod tests {
     use linfa::prelude::Predict;
     #[cfg(not(feature = "blas"))]
     use linfa_linalg::norm::Norm;
-    use ndarray::{arr2, array, Array, Zip};
+    use ndarray::{arr1, arr2, array, Array, Zip};
     #[cfg(feature = "blas")]
     use ndarray_linalg::Norm;
     use ndarray_npy::write_npy;
@@ -1119,7 +1114,7 @@ mod tests {
         let rng = Xoshiro256Plus::seed_from_u64(42);
         let nt = 5;
         let xt = Lhs::new(&xlimits).with_rng(rng).sample(nt);
-        let yt = Array::from_vec(vec![3.1; nt]).insert_axis(Axis(1));
+        let yt = Array::from_vec(vec![3.1; nt]);
         let gp = GaussianProcess::<f64, ConstantMean, SquaredExponentialCorr>::params(
             ConstantMean::default(),
             SquaredExponentialCorr::default(),
@@ -1131,7 +1126,7 @@ mod tests {
         let rng = Xoshiro256Plus::seed_from_u64(43);
         let xtest = Lhs::new(&xlimits).with_rng(rng).sample(nt);
         let ytest = gp.predict(&xtest).expect("prediction error");
-        assert_abs_diff_eq!(Array::from_elem((nt, 1), 3.1), ytest, epsilon = 1e-6);
+        assert_abs_diff_eq!(Array::from_elem((nt,), 3.1), ytest, epsilon = 1e-6);
     }
 
     macro_rules! test_gp {
@@ -1142,7 +1137,7 @@ mod tests {
                 fn [<test_gp_ $regr:snake _ $corr:snake >]() {
                     let xt = array![[0.0], [1.0], [2.0], [3.0], [4.0]];
                     let xplot = Array::linspace(0., 4., 100).insert_axis(Axis(1));
-                    let yt = array![[0.0], [1.0], [1.5], [0.9], [1.0]];
+                    let yt = array![0.0, 1.0, 1.5, 0.9, 1.0];
                     let gp = GaussianProcess::<f64, [<$regr Mean>], [<$corr Corr>] >::params(
                         [<$regr Mean>]::default(),
                         [<$corr Corr>]::default(),
@@ -1153,7 +1148,7 @@ mod tests {
                     let yvals = gp
                         .predict(&arr2(&[[1.0], [3.5]]))
                         .expect("prediction error");
-                    let expected_y = arr2(&[[1.0], [0.9]]);
+                    let expected_y = arr1(&[1.0, 0.9]);
                     assert_abs_diff_eq!(expected_y, yvals, epsilon = 0.5);
 
                     let gpr_vals = gp.predict(&xplot).unwrap();
@@ -1200,16 +1195,16 @@ mod tests {
     test_gp!(Quadratic, Matern32);
     test_gp!(Quadratic, Matern52);
 
-    fn griewank(x: &Array2<f64>) -> Array2<f64> {
+    fn griewank(x: &Array2<f64>) -> Array1<f64> {
         let dim = x.ncols();
         let d = Array1::linspace(1., dim as f64, dim).mapv(|v| v.sqrt());
-        let mut y = Array2::zeros((x.nrows(), 1));
-        Zip::from(y.rows_mut()).and(x.rows()).for_each(|mut y, x| {
+        let mut y = Array1::zeros((x.nrows(),));
+        Zip::from(&mut y).and(x.rows()).for_each(|y, x| {
             let s = x.mapv(|v| v * v).sum() / 4000.;
             let p = (x.to_owned() / &d)
                 .mapv(|v| v.cos())
                 .fold(1., |acc, x| acc * x);
-            y[0] = s - p + 1.;
+            *y = s - p + 1.;
         });
         y
     }
@@ -1217,11 +1212,7 @@ mod tests {
     #[test]
     fn test_griewank() {
         let x = array![[1., 1., 1., 1., 1.], [2., 2., 2., 2., 2.]];
-        assert_abs_diff_eq!(
-            array![[0.72890641], [1.01387135]],
-            griewank(&x),
-            epsilon = 1e-8
-        );
+        assert_abs_diff_eq!(array![0.72890641, 1.01387135], griewank(&x), epsilon = 1e-8);
     }
 
     #[test]
@@ -1273,10 +1264,8 @@ mod tests {
         });
     }
 
-    fn tensor_product_exp(x: &ArrayBase<impl Data<Elem = f64>, Ix2>) -> Array2<f64> {
-        x.mapv(|v| v.exp())
-            .map_axis(Axis(1), |row| row.product())
-            .insert_axis(Axis(1))
+    fn tensor_product_exp(x: &ArrayBase<impl Data<Elem = f64>, Ix2>) -> Array1<f64> {
+        x.mapv(|v| v.exp()).map_axis(Axis(1), |row| row.product())
     }
 
     #[test]
@@ -1305,13 +1294,11 @@ mod tests {
         assert_abs_diff_eq!(err, 0., epsilon = 2e-2);
     }
 
-    fn rosenb(x: &ArrayBase<impl Data<Elem = f64>, Ix2>) -> Array2<f64> {
-        let mut y: Array2<f64> = Array2::zeros((x.nrows(), 1));
-        Zip::from(y.rows_mut())
-            .and(x.rows())
-            .par_for_each(|mut yi, xi| {
-                yi.assign(&array![rosenbrock(&xi.to_vec())]);
-            });
+    fn rosenb(x: &ArrayBase<impl Data<Elem = f64>, Ix2>) -> Array1<f64> {
+        let mut y: Array1<f64> = Array1::zeros((x.nrows(),));
+        Zip::from(&mut y).and(x.rows()).par_for_each(|yi, xi| {
+            *yi = rosenbrock(&xi.to_vec());
+        });
         y
     }
 
@@ -1345,20 +1332,16 @@ mod tests {
         assert_abs_diff_eq!(var, Array2::zeros((nt, 1)), epsilon = 2e-1);
     }
 
-    fn sphere(x: &Array2<f64>) -> Array2<f64> {
-        let s = (x * x).sum_axis(Axis(1));
-        s.insert_axis(Axis(1))
+    fn sphere(x: &Array2<f64>) -> Array1<f64> {
+        (x * x).sum_axis(Axis(1))
     }
 
     fn dsphere(x: &Array2<f64>) -> Array2<f64> {
         x.mapv(|v| 2. * v)
     }
 
-    fn norm1(x: &Array2<f64>) -> Array2<f64> {
-        x.mapv(|v| v.abs())
-            .sum_axis(Axis(1))
-            .insert_axis(Axis(1))
-            .to_owned()
+    fn norm1(x: &Array2<f64>) -> Array1<f64> {
+        x.mapv(|v| v.abs()).sum_axis(Axis(1)).to_owned()
     }
 
     fn dnorm1(x: &Array2<f64>) -> Array2<f64> {
@@ -1407,8 +1390,8 @@ mod tests {
                     println!("true deriv at [{},{}] = {}", xa, xb, true_deriv);
                     println!("jacob = at [{},{}] = {}", xa, xb, gp.predict_jacobian(&array![xa, xb]));
 
-                    let diff_g = (y_pred[[1, 0]] - y_pred[[2, 0]]) / (2. * e);
-                    let diff_d = (y_pred[[3, 0]] - y_pred[[4, 0]]) / (2. * e);
+                    let diff_g = (y_pred[1] - y_pred[2]) / (2. * e);
+                    let diff_d = (y_pred[3] - y_pred[4]) / (2. * e);
 
                     // test only if fdiff is not largely wrong
                     if (diff_g-true_deriv[[0, 0]]).abs() < 10. {
@@ -1551,7 +1534,7 @@ mod tests {
     #[test]
     fn test_fixed_theta() {
         let xt = array![[0.0], [1.0], [2.0], [3.0], [4.0]];
-        let yt = array![[0.0], [1.0], [1.5], [0.9], [1.0]];
+        let yt = array![0.0, 1.0, 1.5, 0.9, 1.0];
         let gp = Kriging::params()
             .fit(&Dataset::new(xt.clone(), yt.clone()))
             .expect("GP fit error");
@@ -1566,18 +1549,8 @@ mod tests {
         assert_abs_diff_eq!(*gp.theta().to_vec(), expected);
     }
 
-    #[test]
-    #[should_panic]
-    fn test_multiple_outputs() {
-        let xt = array![[0.0], [1.0], [2.0], [3.0], [4.0]];
-        let yt = array![[0.0, 10.0], [1.0, -3.], [1.5, 1.5], [0.9, 1.0], [1.0, 0.0]];
-        let _gp = Kriging::params()
-            .fit(&Dataset::new(xt.clone(), yt.clone()))
-            .expect("GP fit error");
-    }
-
-    fn x2sinx(x: &Array2<f64>) -> Array2<f64> {
-        (x * x) * (x).mapv(|v| v.sin())
+    fn x2sinx(x: &Array2<f64>) -> Array1<f64> {
+        ((x * x) * (x).mapv(|v| v.sin())).remove_axis(Axis(1))
     }
 
     #[test]
@@ -1661,18 +1634,18 @@ mod tests {
             [-1.875, -0.625]
         ];
         let yt = array![
-            [2.43286801],
-            [13.10840811],
-            [5.32908578],
-            [17.81862219],
-            [74.08849877],
-            [39.68137781],
-            [14.96009727],
-            [63.17475741],
-            [61.26331775],
-            [-7.46009727],
-            [44.39159189],
-            [2.17091422],
+            2.43286801,
+            13.10840811,
+            5.32908578,
+            17.81862219,
+            74.08849877,
+            39.68137781,
+            14.96009727,
+            63.17475741,
+            61.26331775,
+            -7.46009727,
+            44.39159189,
+            2.17091422,
         ];
 
         let gp = GaussianProcess::<f64, ConstantMean, SquaredExponentialCorr>::params(
diff --git a/gp/src/metrics.rs b/gp/src/metrics.rs
index ac57ae81..04cd190d 100644
--- a/gp/src/metrics.rs
+++ b/gp/src/metrics.rs
@@ -3,7 +3,7 @@ use linfa::{
     traits::{Fit, Predict, PredictInplace},
     Float, ParamGuard,
 };
-use ndarray::{Array2, ArrayBase, Ix2, OwnedRepr};
+use ndarray::{Array1, Array2, ArrayBase, Ix2, OwnedRepr};
 
 use crate::{
     correlation_models, mean_models, GaussianProcess, GpError, GpParams, SgpParams,
@@ -15,10 +15,10 @@ pub trait CrossValScore<F, ER, P, O>
 where
     F: Float,
     ER: std::error::Error + From<linfa::error::Error>,
-    P: Fit<Array2<F>, Array2<F>, ER, Object = O> + ParamGuard,
-    O: PredictInplace<ArrayBase<OwnedRepr<F>, Ix2>, Array2<F>>,
+    P: Fit<Array2<F>, Array1<F>, ER, Object = O> + ParamGuard,
+    O: PredictInplace<ArrayBase<OwnedRepr<F>, Ix2>, Array1<F>>,
 {
-    fn training_data(&self) -> &(Array2<F>, Array2<F>);
+    fn training_data(&self) -> &(Array2<F>, Array1<F>);
 
     fn params(&self) -> P;
 
@@ -51,7 +51,7 @@ where
     Mean: mean_models::RegressionModel<F>,
     Corr: correlation_models::CorrelationModel<F>,
 {
-    fn training_data(&self) -> &(Array2<F>, Array2<F>) {
+    fn training_data(&self) -> &(Array2<F>, Array1<F>) {
         &self.training_data
     }
 
@@ -65,7 +65,7 @@ where
     F: Float,
     Corr: correlation_models::CorrelationModel<F>,
 {
-    fn training_data(&self) -> &(Array2<F>, Array2<F>) {
+    fn training_data(&self) -> &(Array2<F>, Array1<F>) {
         &self.training_data
     }
 
@@ -80,22 +80,22 @@ mod test {
     use crate::{Inducings, SparseKriging};
     use approx::assert_abs_diff_eq;
     use egobox_doe::{Lhs, SamplingMethod};
-    use ndarray::{array, Array, Array1, Data, Ix2, Zip};
+    use ndarray::{array, Array, Array1, Axis, Data, Ix2, Zip};
     use ndarray_rand::rand::SeedableRng;
     use ndarray_rand::rand_distr::{Normal, Uniform};
     use ndarray_rand::RandomExt;
     use rand_xoshiro::Xoshiro256Plus;
 
-    fn griewank(x: &Array2<f64>) -> Array2<f64> {
+    fn griewank(x: &Array2<f64>) -> Array1<f64> {
         let dim = x.ncols();
         let d = Array1::linspace(1., dim as f64, dim).mapv(|v| v.sqrt());
-        let mut y = Array2::zeros((x.nrows(), 1));
-        Zip::from(y.rows_mut()).and(x.rows()).for_each(|mut y, x| {
+        let mut y = Array1::zeros((x.nrows(),));
+        Zip::from(&mut y).and(x.rows()).for_each(|y, x| {
             let s = x.mapv(|v| v * v).sum() / 4000.;
             let p = (x.to_owned() / &d)
                 .mapv(|v| v.cos())
                 .fold(1., |acc, x| acc * x);
-            y[0] = s - p + 1.;
+            *y = s - p + 1.;
         });
         y
     }
@@ -142,11 +142,11 @@ mod test {
         nt: usize,
         eta2: f64,
         rng: &mut Xoshiro256Plus,
-    ) -> (Array2<f64>, Array2<f64>) {
+    ) -> (Array2<f64>, Array1<f64>) {
         let normal = Normal::new(0., eta2.sqrt()).unwrap();
         let gaussian_noise = Array::<f64, _>::random_using((nt, 1), normal, rng);
         let xt = 2. * Array::<f64, _>::random_using((nt, 1), Uniform::new(0., 1.), rng) - 1.;
-        let yt = f_obj(&xt) + gaussian_noise;
+        let yt = (f_obj(&xt) + gaussian_noise).remove_axis(Axis(1));
         (xt, yt)
     }
 
diff --git a/gp/src/sparse_algorithm.rs b/gp/src/sparse_algorithm.rs
index 0f8bc6e4..607a91b8 100644
--- a/gp/src/sparse_algorithm.rs
+++ b/gp/src/sparse_algorithm.rs
@@ -7,7 +7,7 @@ use finitediff::FiniteDiff;
 use linfa::prelude::{Dataset, DatasetBase, Fit, Float, PredictInplace};
 use linfa_linalg::{cholesky::*, triangular::*};
 use linfa_pls::PlsRegression;
-use ndarray::{s, Array, Array1, Array2, ArrayBase, ArrayView2, Axis, Data, Ix2, Zip};
+use ndarray::{s, Array, Array1, Array2, ArrayBase, ArrayView2, Axis, Data, Ix1, Ix2, Zip};
 use ndarray_einsum_beta::*;
 use ndarray_rand::rand::seq::SliceRandom;
 use ndarray_rand::rand::SeedableRng;
@@ -71,7 +71,7 @@ impl<F: Float> Clone for WoodburyData<F> {
 /// # Example
 ///
 /// ```
-/// use ndarray::{Array, Array2, Axis};
+/// use ndarray::{Array, Array1, Array2, Axis};
 /// use ndarray_rand::rand;
 /// use ndarray_rand::rand::SeedableRng;
 /// use ndarray_rand::RandomExt;
@@ -83,8 +83,8 @@ impl<F: Float> Clone for WoodburyData<F> {
 /// const PI: f64 = std::f64::consts::PI;
 ///
 /// // Let us define a hidden target function for our sparse GP example
-/// fn f_obj(x: &Array2<f64>) -> Array2<f64> {
-///   x.mapv(|v| (3. * PI * v).sin() + 0.3 * (9. * PI * v).cos() + 0.5 * (7. * PI * v).sin())
+/// fn f_obj(x: &Array1<f64>) -> Array1<f64> {
+///     x.mapv(|v| (3. * PI * v).sin() + 0.3 * (9. * PI * v).cos() + 0.5 * (7. * PI * v).sin())
 /// }
 ///
 /// // Then we can define a utility function to generate some noisy data
@@ -92,13 +92,13 @@ impl<F: Float> Clone for WoodburyData<F> {
 /// fn make_test_data(
 ///     nt: usize,
 ///     eta2: f64,
-/// ) -> (Array2<f64>, Array2<f64>) {
+/// ) -> (Array2<f64>, Array1<f64>) {
 ///     let normal = Normal::new(0., eta2.sqrt()).unwrap();
 ///     let mut rng = rand::thread_rng();
-///     let gaussian_noise = Array::<f64, _>::random_using((nt, 1), normal, &mut rng);
-///     let xt = 2. * Array::<f64, _>::random_using((nt, 1), Uniform::new(0., 1.), &mut rng) - 1.;
+///     let gaussian_noise = Array::<f64, _>::random_using((nt, ), normal, &mut rng);
+///     let xt = 2. * Array::<f64, _>::random_using((nt, ), Uniform::new(0., 1.), &mut rng) - 1.;
 ///     let yt = f_obj(&xt) + gaussian_noise;
-///     (xt, yt)
+///     (xt.insert_axis(Axis(1)), yt)
 /// }
 ///
 /// // Generate training data
@@ -163,7 +163,7 @@ pub struct SparseGaussianProcess<F: Float, Corr: CorrelationModel<F>> {
     /// Data used for prediction
     w_data: WoodburyData<F>,
     /// Training data (input, output)
-    pub(crate) training_data: (Array2<F>, Array2<F>),
+    pub(crate) training_data: (Array2<F>, Array1<F>),
     /// Parameters used to fit this model
     pub(crate) params: SgpValidParams<F, Corr>,
 }
@@ -232,10 +232,10 @@ impl<F: Float, Corr: CorrelationModel<F>> SparseGaussianProcess<F, Corr> {
     }
 
     /// Predict output values at n given `x` points of nx components specified as a (n, nx) matrix.
-    /// Returns n scalar output values as (n, 1) column vector.
-    pub fn predict(&self, x: &ArrayBase<impl Data<Elem = F>, Ix2>) -> Result<Array2<F>> {
+    /// Returns n scalar output values as as a vector (n,).
+    pub fn predict(&self, x: &ArrayBase<impl Data<Elem = F>, Ix2>) -> Result<Array1<F>> {
         let kx = self.compute_k(x, &self.inducings, &self.w_star, &self.theta, self.sigma2);
-        let mu = kx.dot(&self.w_data.vec);
+        let mu = kx.dot(&self.w_data.vec).remove_axis(Axis(1));
         Ok(mu)
     }
 
@@ -291,14 +291,14 @@ impl<F: Float, Corr: CorrelationModel<F>> SparseGaussianProcess<F, Corr> {
 
     /// Retrieve input and output dimensions
     pub fn dims(&self) -> (usize, usize) {
-        (self.training_data.0.ncols(), self.training_data.1.ncols())
+        (self.training_data.0.ncols(), self.training_data.1.len())
     }
 
     pub fn predict_gradients(&self, x: &ArrayBase<impl Data<Elem = F>, Ix2>) -> Array2<F> {
         let mut drv = Array2::<F>::zeros((x.nrows(), self.training_data.0.ncols()));
         let f = |x: &Array1<f64>| -> f64 {
             let x = x.to_owned().insert_axis(Axis(0)).mapv(|v| F::cast(v));
-            let v = self.predict(&x).unwrap()[[0, 0]];
+            let v = self.predict(&x).unwrap()[0];
             unsafe { *(&v as *const F as *const f64) }
         };
         Zip::from(drv.rows_mut())
@@ -348,22 +348,22 @@ impl<F: Float, Corr: CorrelationModel<F>> SparseGaussianProcess<F, Corr> {
         n_traj: usize,
         method: GpSamplingMethod,
     ) -> Array2<F> {
-        let mean = self.predict(x).unwrap();
+        let mean = self.predict(x).unwrap().insert_axis(Axis(1));
         let cov = self.compute_k(x, x, &self.w_star, &self.theta, self.sigma2);
         sample(x, mean, cov, n_traj, method)
     }
 }
 
-impl<F, D, Corr> PredictInplace<ArrayBase<D, Ix2>, Array2<F>> for SparseGaussianProcess<F, Corr>
+impl<F, D, Corr> PredictInplace<ArrayBase<D, Ix2>, Array1<F>> for SparseGaussianProcess<F, Corr>
 where
     F: Float,
     D: Data<Elem = F>,
     Corr: CorrelationModel<F>,
 {
-    fn predict_inplace(&self, x: &ArrayBase<D, Ix2>, y: &mut Array2<F>) {
+    fn predict_inplace(&self, x: &ArrayBase<D, Ix2>, y: &mut Array1<F>) {
         assert_eq!(
             x.nrows(),
-            y.nrows(),
+            y.len(),
             "The number of data points must match the number of output targets."
         );
 
@@ -371,8 +371,8 @@ where
         *y = values;
     }
 
-    fn default_target(&self, x: &ArrayBase<D, Ix2>) -> Array2<F> {
-        Array2::zeros((x.nrows(), self.dims().1))
+    fn default_target(&self, x: &ArrayBase<D, Ix2>) -> Array1<F> {
+        Array1::zeros((x.nrows(),))
     }
 }
 
@@ -407,23 +407,18 @@ where
 }
 
 impl<F: Float, Corr: CorrelationModel<F>, D: Data<Elem = F> + Sync>
-    Fit<ArrayBase<D, Ix2>, ArrayBase<D, Ix2>, GpError> for SgpValidParams<F, Corr>
+    Fit<ArrayBase<D, Ix2>, ArrayBase<D, Ix1>, GpError> for SgpValidParams<F, Corr>
 {
     type Object = SparseGaussianProcess<F, Corr>;
 
     /// Fit GP parameters using maximum likelihood
     fn fit(
         &self,
-        dataset: &DatasetBase<ArrayBase<D, Ix2>, ArrayBase<D, Ix2>>,
+        dataset: &DatasetBase<ArrayBase<D, Ix2>, ArrayBase<D, Ix1>>,
     ) -> Result<Self::Object> {
         let x = dataset.records();
-        let y = dataset.targets();
-        if y.ncols() > 1 {
-            panic!(
-                "Multiple outputs not handled, a one-dimensional column vector \
-            as training output data is expected"
-            );
-        }
+        let y = dataset.targets().to_owned().insert_axis(Axis(1));
+
         if let Some(d) = self.kpls_dim() {
             if *d > x.ncols() {
                 return Err(GpError::InvalidValueError(format!(
@@ -440,7 +435,7 @@ impl<F: Float, Corr: CorrelationModel<F>, D: Data<Elem = F> + Sync>
 
         let mut w_star = Array2::eye(x.ncols());
         if let Some(n_components) = self.kpls_dim() {
-            let ds = Dataset::new(x.to_owned(), y.to_owned());
+            let ds = Dataset::new(xtrain.to_owned(), ytrain.to_owned());
             w_star = PlsRegression::params(*n_components).fit(&ds).map_or_else(
                 |e| match e {
                     linfa_pls::PlsError::PowerMethodConstantResidualError() => {
@@ -634,7 +629,7 @@ impl<F: Float, Corr: CorrelationModel<F>, D: Data<Elem = F> + Sync>
             w_data,
             w_star,
             inducings: z.clone(),
-            training_data: (xtrain.to_owned(), ytrain.to_owned()),
+            training_data: (xtrain.to_owned(), ytrain.remove_axis(Axis(1))),
             params: self.clone(),
         })
     }
@@ -862,12 +857,12 @@ mod tests {
         nt: usize,
         eta2: f64,
         rng: &mut Xoshiro256Plus,
-    ) -> (Array2<f64>, Array2<f64>) {
+    ) -> (Array2<f64>, Array1<f64>) {
         let normal = Normal::new(0., eta2.sqrt()).unwrap();
         let gaussian_noise = Array::<f64, _>::random_using((nt, 1), normal, rng);
         let xt = 2. * Array::<f64, _>::random_using((nt, 1), Uniform::new(0., 1.), rng) - 1.;
         let yt = f_obj(&xt) + gaussian_noise;
-        (xt, yt)
+        (xt, yt.remove_axis(Axis(1)))
     }
 
     fn save_data(
@@ -928,7 +923,7 @@ mod tests {
         println!("noise variance={:?}", sgp.noise_variance());
         // assert_abs_diff_eq!(eta2, sgp.noise_variance());
 
-        let sgp_vals = sgp.predict(&xplot).unwrap();
+        let sgp_vals = sgp.predict(&xplot).unwrap().insert_axis(Axis(1));
         let yplot = f_obj(&xplot);
         let errvals = (yplot - &sgp_vals).mapv(|v| v.abs());
         assert_abs_diff_eq!(errvals, Array2::zeros((xplot.nrows(), 1)), epsilon = 0.5);
@@ -936,7 +931,14 @@ mod tests {
         let errvars = (&sgp_vars - Array2::from_elem((xplot.nrows(), 1), 0.01)).mapv(|v| v.abs());
         assert_abs_diff_eq!(errvars, Array2::zeros((xplot.nrows(), 1)), epsilon = 0.2);
 
-        save_data(&xt, &yt, sgp.inducings(), &xplot, &sgp_vals, &sgp_vars);
+        save_data(
+            &xt,
+            &yt.insert_axis(Axis(1)),
+            sgp.inducings(),
+            &xplot,
+            &sgp_vals,
+            &sgp_vars,
+        );
     }
 
     #[test]
@@ -974,10 +976,17 @@ mod tests {
         println!("noise variance={:?}", sgp.noise_variance());
         assert_abs_diff_eq!(eta2, sgp.noise_variance());
 
-        let sgp_vals = sgp.predict(&xplot).unwrap();
+        let sgp_vals = sgp.predict(&xplot).unwrap().insert_axis(Axis(1));
         let sgp_vars = sgp.predict_var(&xplot).unwrap();
 
-        save_data(&xt, &yt, sgp.inducings(), &xplot, &sgp_vals, &sgp_vars);
+        save_data(
+            &xt,
+            &yt.insert_axis(Axis(1)),
+            sgp.inducings(),
+            &xplot,
+            &sgp_vals,
+            &sgp_vars,
+        );
     }
 
     #[test]
@@ -1022,10 +1031,17 @@ mod tests {
         assert_abs_diff_eq!(eta2, sgp.noise_variance(), epsilon = 0.015);
         assert_abs_diff_eq!(&z, sgp.inducings(), epsilon = 0.0015);
 
-        let sgp_vals = sgp.predict(&xplot).unwrap();
+        let sgp_vals = sgp.predict(&xplot).unwrap().insert_axis(Axis(1));
         let sgp_vars = sgp.predict_var(&xplot).unwrap();
 
-        save_data(&xt, &yt, &z, &xplot, &sgp_vals, &sgp_vars);
+        save_data(
+            &xt,
+            &yt.insert_axis(Axis(1)),
+            &z,
+            &xplot,
+            &sgp_vals,
+            &sgp_vars,
+        );
     }
 
     #[test]
diff --git a/moe/benches/bench_find_nb_clusters.rs b/moe/benches/bench_find_nb_clusters.rs
index 2284645f..c9c8a479 100644
--- a/moe/benches/bench_find_nb_clusters.rs
+++ b/moe/benches/bench_find_nb_clusters.rs
@@ -2,11 +2,11 @@ use criterion::{criterion_group, criterion_main, Criterion};
 
 use egobox_doe::{Lhs, SamplingMethod};
 use egobox_moe::*;
-use ndarray::{array, Array2, Zip};
+use ndarray::{array, Array1, Array2, Axis, Zip};
 use ndarray_rand::rand::SeedableRng;
 use rand_xoshiro::Xoshiro256Plus;
 
-fn function_test_1d(x: &Array2<f64>) -> Array2<f64> {
+fn function_test_1d(x: &Array2<f64>) -> Array1<f64> {
     let mut y = Array2::zeros(x.dim());
     Zip::from(&mut y).and(x).for_each(|yi, &xi| {
         if xi < 0.4 {
@@ -17,7 +17,7 @@ fn function_test_1d(x: &Array2<f64>) -> Array2<f64> {
             *yi = f64::sin(10. * xi);
         }
     });
-    y
+    y.remove_axis(Axis(1))
 }
 
 fn criterion_benchmark(c: &mut Criterion) {
diff --git a/moe/examples/clustering.rs b/moe/examples/clustering.rs
index 0ef2d8fa..2e7779b2 100644
--- a/moe/examples/clustering.rs
+++ b/moe/examples/clustering.rs
@@ -21,7 +21,7 @@ fn f3parts(x: &Array2<f64>) -> Array2<f64> {
 fn main() -> Result<(), Box<dyn Error>> {
     let xtrain = Lhs::new(&arr2(&[[0., 1.]])).sample(50);
     let ytrain = f3parts(&xtrain);
-    let ds = Dataset::new(xtrain, ytrain);
+    let ds = Dataset::new(xtrain, ytrain.remove_axis(Axis(1)));
     let moe1 = GpMixture::params().fit(&ds)?;
     let moe3 = GpMixture::params()
         .n_clusters(3)
diff --git a/moe/examples/moe_norm1.rs b/moe/examples/moe_norm1.rs
index 11902159..69c03b8b 100644
--- a/moe/examples/moe_norm1.rs
+++ b/moe/examples/moe_norm1.rs
@@ -23,7 +23,7 @@ fn main() -> Result<(), Box<dyn Error>> {
 
     let xtrain = data_train.slice(s![.., ..2_usize]).to_owned();
     let ytrain = data_train.slice(s![.., 2_usize..]).to_owned();
-    let ds = Dataset::new(xtrain, ytrain);
+    let ds = Dataset::new(xtrain, ytrain.remove_axis(Axis(1)));
     let moe = GpMixture::params().n_clusters(4).fit(&ds)?;
 
     let xlimits = arr2(&[[-1., 1.], [-1., 1.]]);
diff --git a/moe/examples/norm1.rs b/moe/examples/norm1.rs
index 60a15e41..2ff05aef 100644
--- a/moe/examples/norm1.rs
+++ b/moe/examples/norm1.rs
@@ -11,7 +11,7 @@ fn norm1(x: &Array2<f64>) -> Array2<f64> {
 fn main() -> Result<(), Box<dyn Error>> {
     let xtrain = Lhs::new(&arr2(&[[-1., 1.], [-1., 1.]])).sample(200);
     let ytrain = norm1(&xtrain);
-    let ds = Dataset::new(xtrain, ytrain);
+    let ds = Dataset::new(xtrain, ytrain.remove_axis(Axis(1)));
     let moe1 = GpMixture::params().fit(&ds)?;
     let moe5 = GpMixture::params()
         .n_clusters(6)
diff --git a/moe/src/algorithm.rs b/moe/src/algorithm.rs
index 226ddaf0..5ce09fd5 100644
--- a/moe/src/algorithm.rs
+++ b/moe/src/algorithm.rs
@@ -21,7 +21,7 @@ use std::ops::Sub;
 #[cfg(not(feature = "blas"))]
 use linfa_linalg::norm::*;
 use ndarray::{
-    concatenate, s, Array1, Array2, Array3, ArrayBase, ArrayView2, Axis, Data, Ix2, Zip,
+    concatenate, s, Array1, Array2, Array3, ArrayBase, ArrayView2, Axis, Data, Ix1, Ix2, Zip,
 };
 
 #[cfg(feature = "blas")]
@@ -46,7 +46,7 @@ macro_rules! check_allowed {
     };
 }
 
-impl<D: Data<Elem = f64>> Fit<ArrayBase<D, Ix2>, ArrayBase<D, Ix2>, MoeError>
+impl<D: Data<Elem = f64>> Fit<ArrayBase<D, Ix2>, ArrayBase<D, Ix1>, MoeError>
     for GpMixtureValidParams<f64>
 {
     type Object = GpMixture;
@@ -60,7 +60,7 @@ impl<D: Data<Elem = f64>> Fit<ArrayBase<D, Ix2>, ArrayBase<D, Ix2>, MoeError>
     ///
     fn fit(
         &self,
-        dataset: &DatasetBase<ArrayBase<D, Ix2>, ArrayBase<D, Ix2>>,
+        dataset: &DatasetBase<ArrayBase<D, Ix2>, ArrayBase<D, Ix1>>,
     ) -> Result<Self::Object> {
         let x = dataset.records();
         let y = dataset.targets();
@@ -72,11 +72,15 @@ impl GpMixtureValidParams<f64> {
     pub fn train(
         &self,
         xt: &ArrayBase<impl Data<Elem = f64>, Ix2>,
-        yt: &ArrayBase<impl Data<Elem = f64>, Ix2>,
+        yt: &ArrayBase<impl Data<Elem = f64>, Ix1>,
     ) -> Result<GpMixture> {
         trace!("Moe training...");
         let nx = xt.ncols();
-        let data = concatenate(Axis(1), &[xt.view(), yt.view()]).unwrap();
+        let data = concatenate(
+            Axis(1),
+            &[xt.view(), yt.to_owned().insert_axis(Axis(1)).view()],
+        )
+        .unwrap();
 
         let (n_clusters, recomb) = if self.n_clusters() == 0 {
             // automatic mode
@@ -98,7 +102,7 @@ impl GpMixtureValidParams<f64> {
         }
 
         let training = if recomb == Recombination::Smooth(None) && self.n_clusters() > 1 {
-            // Extract 5% of data for validation
+            // Extract 5% of data for validation to find best heaviside factor
             // TODO: Use cross-validation ? Performances
             let (_, training_data) = extract_part(&data, 5);
             training_data
@@ -138,13 +142,17 @@ impl GpMixtureValidParams<f64> {
     pub fn train_on_clusters(
         &self,
         xt: &ArrayBase<impl Data<Elem = f64>, Ix2>,
-        yt: &ArrayBase<impl Data<Elem = f64>, Ix2>,
+        yt: &ArrayBase<impl Data<Elem = f64>, Ix1>,
         clustering: &Clustering,
     ) -> Result<GpMixture> {
         let gmx = clustering.gmx();
         let recomb = clustering.recombination();
         let nx = xt.ncols();
-        let data = concatenate(Axis(1), &[xt.view(), yt.view()]).unwrap();
+        let data = concatenate(
+            Axis(1),
+            &[xt.view(), yt.to_owned().insert_axis(Axis(1)).view()],
+        )
+        .unwrap();
 
         let dataset_clustering = gmx.predict(xt);
         let clusters = sort_by_cluster(gmx.n_clusters(), &data, &dataset_clustering);
@@ -167,11 +175,11 @@ impl GpMixtureValidParams<f64> {
         }
 
         if recomb == Recombination::Smooth(None) && self.n_clusters() > 1 {
-            // Extract 5% of data for validation
+            // Extract 5% of data for validation to find best heaviside factor
             // TODO: Use cross-validation ? Performances
             let (test, _) = extract_part(&data, 5);
             let xtest = test.slice(s![.., ..nx]).to_owned();
-            let ytest = test.slice(s![.., nx..]).to_owned();
+            let ytest = test.slice(s![.., nx..]).to_owned().remove_axis(Axis(1));
             let factor = self.optimize_heaviside_factor(&experts, gmx, &xtest, &ytest);
             info!("Retrain mixture with optimized heaviside factor={}", factor);
 
@@ -204,7 +212,7 @@ impl GpMixtureValidParams<f64> {
     ) -> Result<Box<dyn FullGpSurrogate>> {
         let xtrain = data.slice(s![.., ..nx]).to_owned();
         let ytrain = data.slice(s![.., nx..]).to_owned();
-        let mut dataset = Dataset::from((xtrain.clone(), ytrain.clone()));
+        let mut dataset = Dataset::from((xtrain.clone(), ytrain.clone().remove_axis(Axis(1))));
         let regression_spec = self.regression_spec();
         let mut allowed_means = vec![];
         check_allowed!(regression_spec, Regression, Constant, allowed_means);
@@ -283,6 +291,7 @@ impl GpMixtureValidParams<f64> {
                 if nc > 0 && self.theta_tunings().len() == 1 {
                     expert_params.theta_tuning(self.theta_tunings()[0].clone());
                 } else {
+                    debug!("Training with theta_tuning = {:?}.", self.theta_tunings());
                     expert_params.theta_tuning(self.theta_tunings()[nc].clone());
                 }
                 debug!("Train best expert...");
@@ -337,7 +346,7 @@ impl GpMixtureValidParams<f64> {
         experts: &[Box<dyn FullGpSurrogate>],
         gmx: &GaussianMixture<f64>,
         xtest: &ArrayBase<impl Data<Elem = f64>, Ix2>,
-        ytest: &ArrayBase<impl Data<Elem = f64>, Ix2>,
+        ytest: &ArrayBase<impl Data<Elem = f64>, Ix1>,
     ) -> f64 {
         if self.recombination() == Recombination::Hard || self.n_clusters() == 1 {
             1.
@@ -346,7 +355,7 @@ impl GpMixtureValidParams<f64> {
             let errors = scale_factors.map(move |&factor| {
                 let gmx2 = gmx.clone();
                 let gmx2 = gmx2.heaviside_factor(factor);
-                let pred = predict_smooth(experts, &gmx2, xtest, ytest.ncols()).unwrap();
+                let pred = predict_smooth(experts, &gmx2, xtest).unwrap();
                 pred.sub(ytest).mapv(|x| x * x).sum().sqrt() / xtest.mapv(|x| x * x).sum().sqrt()
             });
 
@@ -387,16 +396,13 @@ fn predict_smooth(
     experts: &[Box<dyn FullGpSurrogate>],
     gmx: &GaussianMixture<f64>,
     points: &ArrayBase<impl Data<Elem = f64>, Ix2>,
-    ny: usize,
-) -> Result<Array2<f64>> {
+) -> Result<Array1<f64>> {
     let probas = gmx.predict_probas(points);
-    let preds: Array2<f64> = experts
+    let preds: Array1<f64> = experts
         .iter()
         .enumerate()
-        .map(|(i, gp)| {
-            gp.predict(&points.view()).unwrap() * probas.column(i).to_owned().insert_axis(Axis(1))
-        })
-        .fold(Array2::zeros((points.nrows(), ny)), |acc, pred| acc + pred);
+        .map(|(i, gp)| gp.predict(&points.view()).unwrap() * probas.column(i))
+        .fold(Array1::zeros((points.nrows(),)), |acc, pred| acc + pred);
     Ok(preds)
 }
 
@@ -415,7 +421,7 @@ pub struct GpMixture {
     /// Gp type
     gp_type: GpType<f64>,
     /// Training inputs
-    training_data: (Array2<f64>, Array2<f64>),
+    training_data: (Array2<f64>, Array1<f64>),
     /// Params used to fit this model
     params: GpMixtureValidParams<f64>,
 }
@@ -463,7 +469,7 @@ impl GpSurrogate for GpMixture {
         self.experts[0].dims()
     }
 
-    fn predict(&self, x: &ArrayView2<f64>) -> Result<Array2<f64>> {
+    fn predict(&self, x: &ArrayView2<f64>) -> Result<Array1<f64>> {
         match self.recombination {
             Recombination::Hard => self.predict_hard(x),
             Recombination::Smooth(_) => self.predict_smooth(x),
@@ -519,7 +525,7 @@ impl GpSurrogateExt for GpMixture {
 }
 
 impl CrossValScore<f64, MoeError, GpMixtureParams<f64>, Self> for GpMixture {
-    fn training_data(&self) -> &(Array2<f64>, Array2<f64>) {
+    fn training_data(&self) -> &(Array2<f64>, Array1<f64>) {
         &self.training_data
     }
 
@@ -556,12 +562,6 @@ impl GpMixture {
         &self.gmx
     }
 
-    /// Retrieve output dimension
-    pub fn output_dim(&self) -> usize {
-        let (_, res) = self.experts[0].dims();
-        res
-    }
-
     /// Sets recombination mode
     pub fn set_recombination(mut self, recombination: Recombination<f64>) -> Self {
         self.recombination = match recombination {
@@ -591,8 +591,8 @@ impl GpMixture {
     /// Gaussian Mixture is used to get the probability of the point to belongs to one cluster
     /// or another (ie responsabilities).     
     /// The smooth recombination of each cluster expert responsabilty is used to get the result.
-    pub fn predict_smooth(&self, x: &ArrayBase<impl Data<Elem = f64>, Ix2>) -> Result<Array2<f64>> {
-        predict_smooth(&self.experts, &self.gmx, x, self.output_dim())
+    pub fn predict_smooth(&self, x: &ArrayBase<impl Data<Elem = f64>, Ix2>) -> Result<Array1<f64>> {
+        predict_smooth(&self.experts, &self.gmx, x)
     }
 
     /// Predict variances at a set of points `x` specified as (n, nx) matrix.
@@ -612,10 +612,7 @@ impl GpMixture {
                 let p = probas.column(i).to_owned().insert_axis(Axis(1));
                 gp.predict_var(&x.view()).unwrap() * &p * &p
             })
-            .fold(
-                Array2::zeros((x.nrows(), self.output_dim())),
-                |acc, pred| acc + pred,
-            );
+            .fold(Array2::zeros((x.nrows(), 1)), |acc, pred| acc + pred);
         Ok(preds)
     }
 
@@ -640,7 +637,7 @@ impl GpMixture {
                 let preds: Array1<f64> = self
                     .experts
                     .iter()
-                    .map(|gp| gp.predict(&x).unwrap()[[0, 0]])
+                    .map(|gp| gp.predict(&x).unwrap()[0])
                     .collect();
                 let drvs: Vec<Array1<f64>> = self
                     .experts
@@ -721,21 +718,14 @@ impl GpMixture {
     /// Gaussian Mixture is used to get the cluster where the point belongs (highest responsability)
     /// Then the expert of the cluster is used to predict the output value.
     /// Returns the ouputs as a (n, 1) column vector
-    pub fn predict_hard(&self, x: &ArrayBase<impl Data<Elem = f64>, Ix2>) -> Result<Array2<f64>> {
+    pub fn predict_hard(&self, x: &ArrayBase<impl Data<Elem = f64>, Ix2>) -> Result<Array1<f64>> {
         let clustering = self.gmx.predict(x);
         trace!("Clustering {:?}", clustering);
-        let mut preds = Array2::zeros((x.nrows(), self.output_dim()));
-        Zip::from(preds.rows_mut())
+        let mut preds = Array1::zeros((x.nrows(),));
+        Zip::from(&mut preds)
             .and(x.rows())
             .and(&clustering)
-            .for_each(|mut y, x, &c| {
-                y.assign(
-                    &self.experts[c]
-                        .predict(&x.insert_axis(Axis(0)))
-                        .unwrap()
-                        .row(0),
-                );
-            });
+            .for_each(|y, x, &c| *y = self.experts[c].predict(&x.insert_axis(Axis(0))).unwrap()[0]);
         Ok(preds)
     }
 
@@ -749,7 +739,7 @@ impl GpMixture {
     ) -> Result<Array2<f64>> {
         let clustering = self.gmx.predict(x);
         trace!("Clustering {:?}", clustering);
-        let mut variances = Array2::zeros((x.nrows(), self.output_dim()));
+        let mut variances = Array2::zeros((x.nrows(), 1));
         Zip::from(variances.rows_mut())
             .and(x.rows())
             .and(&clustering)
@@ -819,7 +809,7 @@ impl GpMixture {
         self.experts[ith].sample(&x.view(), n_traj)
     }
 
-    pub fn predict(&self, x: &ArrayBase<impl Data<Elem = f64>, Ix2>) -> Result<Array2<f64>> {
+    pub fn predict(&self, x: &ArrayBase<impl Data<Elem = f64>, Ix2>) -> Result<Array1<f64>> {
         <GpMixture as GpSurrogate>::predict(self, &x.view())
     }
 
@@ -897,11 +887,11 @@ fn extract_part<F: Float>(
     (data_test, data_train)
 }
 
-impl<D: Data<Elem = f64>> PredictInplace<ArrayBase<D, Ix2>, Array2<f64>> for GpMixture {
-    fn predict_inplace(&self, x: &ArrayBase<D, Ix2>, y: &mut Array2<f64>) {
+impl<D: Data<Elem = f64>> PredictInplace<ArrayBase<D, Ix2>, Array1<f64>> for GpMixture {
+    fn predict_inplace(&self, x: &ArrayBase<D, Ix2>, y: &mut Array1<f64>) {
         assert_eq!(
             x.nrows(),
-            y.nrows(),
+            y.len(),
             "The number of data points must match the number of output targets."
         );
 
@@ -909,8 +899,8 @@ impl<D: Data<Elem = f64>> PredictInplace<ArrayBase<D, Ix2>, Array2<f64>> for GpM
         *y = values;
     }
 
-    fn default_target(&self, x: &ArrayBase<D, Ix2>) -> Array2<f64> {
-        Array2::zeros((x.nrows(), self.dims().1))
+    fn default_target(&self, x: &ArrayBase<D, Ix2>) -> Array1<f64> {
+        Array1::zeros(x.nrows())
     }
 }
 
@@ -949,7 +939,7 @@ mod tests {
     use ndarray_rand::RandomExt;
     use rand_xoshiro::Xoshiro256Plus;
 
-    fn f_test_1d(x: &Array2<f64>) -> Array2<f64> {
+    fn f_test_1d(x: &Array2<f64>) -> Array1<f64> {
         let mut y = Array2::zeros(x.dim());
         Zip::from(&mut y).and(x).for_each(|yi, &xi| {
             if xi < 0.4 {
@@ -960,7 +950,7 @@ mod tests {
                 *yi = f64::sin(10. * xi);
             }
         });
-        y
+        y.remove_axis(Axis(1))
     }
 
     fn df_test_1d(x: &Array2<f64>) -> Array2<f64> {
@@ -981,7 +971,7 @@ mod tests {
     fn test_moe_hard() {
         let mut rng = Xoshiro256Plus::seed_from_u64(0);
         let xt = Array2::random_using((50, 1), Uniform::new(0., 1.), &mut rng);
-        let yt = f_test_1d(&xt);
+        let yt = f_test_1d(&xt.to_owned());
         let moe = GpMixture::params()
             .n_clusters(3)
             .regression_spec(RegressionSpec::CONSTANT)
@@ -1001,12 +991,12 @@ mod tests {
         write_npy(format!("{test_dir}/dpreds_hard.npy"), &dpreds).expect("dpreds saved");
         assert_abs_diff_eq!(
             0.39 * 0.39,
-            moe.predict(&array![[0.39]]).unwrap()[[0, 0]],
+            moe.predict(&array![[0.39]]).unwrap()[0],
             epsilon = 1e-4
         );
         assert_abs_diff_eq!(
             f64::sin(10. * 0.82),
-            moe.predict(&array![[0.82]]).unwrap()[[0, 0]],
+            moe.predict(&array![[0.82]]).unwrap()[0],
             epsilon = 1e-4
         );
         println!("LOOCV = {}", moe.loocv_score());
@@ -1036,7 +1026,7 @@ mod tests {
         println!("Smooth moe {moe}");
         assert_abs_diff_eq!(
             0.2623, // test we are not good as the true value = 0.37*0.37 = 0.1369
-            moe.predict(&array![[0.37]]).unwrap()[[0, 0]],
+            moe.predict(&array![[0.37]]).unwrap()[0],
             epsilon = 1e-3
         );
 
@@ -1056,17 +1046,17 @@ mod tests {
         write_npy(format!("{test_dir}/preds_smooth2.npy"), &preds).expect("preds saved");
         assert_abs_diff_eq!(
             0.37 * 0.37, // true value of the function
-            moe.predict(&array![[0.37]]).unwrap()[[0, 0]],
+            moe.predict(&array![[0.37]]).unwrap()[0],
             epsilon = 1e-3
         );
     }
 
     #[test]
     fn test_moe_auto() {
-        let mut rng = Xoshiro256Plus::seed_from_u64(0);
-        let xt = Array2::random_using((100, 1), Uniform::new(0., 1.), &mut rng);
+        let mut rng = Xoshiro256Plus::seed_from_u64(42);
+        let xt = Array2::random_using((60, 1), Uniform::new(0., 1.), &mut rng);
         let yt = f_test_1d(&xt);
-        let ds = Dataset::new(xt, yt);
+        let ds = Dataset::new(xt, yt.to_owned());
         let moe = GpMixture::params()
             .n_clusters(0)
             .with_rng(rng.clone())
@@ -1079,7 +1069,7 @@ mod tests {
         );
         assert_abs_diff_eq!(
             0.37 * 0.37, // true value of the function
-            moe.predict(&array![[0.37]]).unwrap()[[0, 0]],
+            moe.predict(&array![[0.37]]).unwrap()[0],
             epsilon = 1e-3
         );
     }
@@ -1186,7 +1176,7 @@ mod tests {
 
             let x = array![[x1], [x1 + h], [x1 - h]];
             let preds = moe.predict(&x).unwrap();
-            let fdiff = (preds[[1, 0]] - preds[[2, 0]]) / (2. * h);
+            let fdiff = (preds[1] - preds[2]) / (2. * h);
 
             let drv = moe.predict_gradients(&xtest).unwrap();
             let df = df_test_1d(&xtest);
@@ -1231,7 +1221,7 @@ mod tests {
             .correlation_spec(CorrelationSpec::SQUAREDEXPONENTIAL)
             .recombination(Recombination::Smooth(Some(1.)))
             .with_rng(rng)
-            .fit(&Dataset::new(xt, yt))
+            .fit(&Dataset::new(xt, yt.remove_axis(Axis(1))))
             .expect("MOE fitted");
 
         for _ in 0..20 {
@@ -1253,8 +1243,8 @@ mod tests {
             let y_pred = moe.predict(&x).unwrap();
             let y_deriv = moe.predict_gradients(&x).unwrap();
 
-            let diff_g = (y_pred[[1, 0]] - y_pred[[2, 0]]) / (2. * e);
-            let diff_d = (y_pred[[3, 0]] - y_pred[[4, 0]]) / (2. * e);
+            let diff_g = (y_pred[1] - y_pred[2]) / (2. * e);
+            let diff_d = (y_pred[3] - y_pred[4]) / (2. * e);
 
             assert_rel_or_abs_error(y_deriv[[0, 0]], diff_g);
             assert_rel_or_abs_error(y_deriv[[0, 1]], diff_d);
@@ -1310,16 +1300,16 @@ mod tests {
         println!("Display moe: {}", moe);
     }
 
-    fn griewank(x: &Array2<f64>) -> Array2<f64> {
+    fn griewank(x: &Array2<f64>) -> Array1<f64> {
         let dim = x.ncols();
         let d = Array1::linspace(1., dim as f64, dim).mapv(|v| v.sqrt());
-        let mut y = Array2::zeros((x.nrows(), 1));
-        Zip::from(y.rows_mut()).and(x.rows()).for_each(|mut y, x| {
+        let mut y = Array1::zeros((x.nrows(),));
+        Zip::from(&mut y).and(x.rows()).for_each(|y, x| {
             let s = x.mapv(|v| v * v).sum() / 4000.;
             let p = (x.to_owned() / &d)
                 .mapv(|v| v.cos())
                 .fold(1., |acc, x| acc * x);
-            y[0] = s - p + 1.;
+            *y = s - p + 1.;
         });
         y
     }
diff --git a/moe/src/clustering.rs b/moe/src/clustering.rs
index e02dfcdd..115481cc 100644
--- a/moe/src/clustering.rs
+++ b/moe/src/clustering.rs
@@ -7,7 +7,7 @@ use linfa::dataset::{Dataset, DatasetView};
 use linfa::traits::{Fit, Predict};
 use linfa::Float;
 use linfa_clustering::GaussianMixtureModel;
-use ndarray::{concatenate, Array1, Array2, ArrayBase, Axis, Data, Ix2, Zip};
+use ndarray::{concatenate, Array1, Array2, ArrayBase, Axis, Data, Ix1, Ix2, Zip};
 use ndarray_rand::rand::Rng;
 use std::ops::Sub;
 
@@ -58,7 +58,7 @@ pub(crate) fn sort_by_cluster<F: Float>(
 /// Find the best number of cluster thanks to cross validation
 pub fn find_best_number_of_clusters<R: Rng + Clone>(
     x: &ArrayBase<impl Data<Elem = f64>, Ix2>,
-    y: &ArrayBase<impl Data<Elem = f64>, Ix2>,
+    y: &ArrayBase<impl Data<Elem = f64>, Ix1>,
     max_nb_clusters: usize,
     kpls_dim: Option<usize>,
     regression_spec: RegressionSpec,
@@ -70,7 +70,7 @@ pub fn find_best_number_of_clusters<R: Rng + Clone>(
     } else {
         max_nb_clusters
     };
-    let dataset: DatasetView<f64, f64> = DatasetView::new(x.view(), y.view());
+    let dataset: DatasetView<f64, f64, Ix1> = DatasetView::new(x.view(), y.view());
 
     // Stock
     let mut mean_err_h: Vec<f64> = Vec::new();
@@ -111,7 +111,13 @@ pub fn find_best_number_of_clusters<R: Rng + Clone>(
         let n_clusters = i + 1;
 
         if ok {
-            let xydata = Dataset::from(concatenate(Axis(1), &[x.view(), y.view()]).unwrap());
+            let xydata = Dataset::from(
+                concatenate(
+                    Axis(1),
+                    &[x.view(), y.to_owned().insert_axis(Axis(1)).view()],
+                )
+                .unwrap(),
+            );
             let maybe_gmm = GaussianMixtureModel::params(n_clusters)
                 .n_runs(20)
                 .with_rng(rng.clone())
@@ -129,9 +135,14 @@ pub fn find_best_number_of_clusters<R: Rng + Clone>(
                         .gmm(gmm.clone())
                         .fit(&train)
                     {
-                        let xytrain =
-                            concatenate(Axis(1), &[train.records().view(), train.targets.view()])
-                                .unwrap();
+                        let xytrain = concatenate(
+                            Axis(1),
+                            &[
+                                train.records().view(),
+                                train.targets.view().insert_axis(Axis(1)),
+                            ],
+                        )
+                        .unwrap();
                         let data_clustering = gmm.predict(&xytrain);
                         let clusters = sort_by_cluster(n_clusters, &xytrain, &data_clustering);
                         for cluster in clusters.iter().take(i + 1) {
@@ -159,7 +170,9 @@ pub fn find_best_number_of_clusters<R: Rng + Clone>(
                             1.0
                         };
                         h_errors.push(h_error);
-                        let mixture = mixture.set_recombination(Recombination::Smooth(None));
+
+                        // Try only default soft(1.0), not soft(None) which can take too much time
+                        let mixture = mixture.set_recombination(Recombination::Smooth(Some(1.)));
                         let s_error = if let Ok(pred) = mixture.predict(valid.records()) {
                             if pred.iter().any(|v| f64::is_infinite(*v)) {
                                 1.0 // max bad value
@@ -196,10 +209,7 @@ pub fn find_best_number_of_clusters<R: Rng + Clone>(
         if ok && !s_errors.is_empty() && !h_errors.is_empty() {
             nb_clusters_ok.push(i);
         } else {
-            // Assume that if it fails for n clusters it will fail for m > n clusters
-            // early exit
             debug!("Prediction with {} clusters fails", n_clusters);
-            break;
         }
 
         // Stock median errors
@@ -357,11 +367,11 @@ mod tests {
     use ndarray_rand::rand::SeedableRng;
     use rand_xoshiro::Xoshiro256Plus;
 
-    fn l1norm(x: &Array2<f64>) -> Array2<f64> {
-        x.map_axis(Axis(1), |x| x.norm_l1()).insert_axis(Axis(1))
+    fn l1norm(x: &Array2<f64>) -> Array1<f64> {
+        x.map_axis(Axis(1), |x| x.norm_l1())
     }
 
-    fn function_test_1d(x: &Array2<f64>) -> Array2<f64> {
+    fn function_test_1d(x: &Array2<f64>) -> Array1<f64> {
         let mut y = Array2::zeros(x.dim());
         Zip::from(&mut y).and(x).for_each(|yi, &xi| {
             if xi < 0.4 {
@@ -372,7 +382,7 @@ mod tests {
                 *yi = f64::sin(10. * xi);
             }
         });
-        y
+        y.remove_axis(Axis(1))
     }
 
     #[test]
diff --git a/moe/src/lib.rs b/moe/src/lib.rs
index 50d5c506..cd3699c2 100644
--- a/moe/src/lib.rs
+++ b/moe/src/lib.rs
@@ -48,8 +48,8 @@
 //! use linfa::{traits::Fit, ParamGuard, Dataset};
 //!
 //! // One-dimensional test function with 3 modes
-//! fn f3modes(x: &Array2<f64>) -> Array2<f64> {
-//!     let mut y = Array2::zeros(x.dim());
+//! fn f3modes(x: &Array1<f64>) -> Array1<f64> {
+//!     let mut y = Array1::zeros(x.len());
 //!     Zip::from(&mut y).and(x).for_each(|yi, &xi| {
 //!         if xi < 0.4 {
 //!             *yi = xi * xi;
@@ -64,9 +64,9 @@
 //!
 //! // Training data
 //! let mut rng = Xoshiro256Plus::from_entropy();
-//! let xt = Array2::random_using((50, 1), Uniform::new(0., 1.), &mut rng);
+//! let xt = Array1::random_using((50, ), Uniform::new(0., 1.), &mut rng);
 //! let yt = f3modes(&xt);
-//! let ds = Dataset::new(xt, yt);
+//! let ds = Dataset::new(xt.insert_axis(Axis(1)), yt);
 //!
 //! // Predictions
 //! let observations = Array1::linspace(0., 1., 100).insert_axis(Axis(1));
diff --git a/moe/src/surrogates.rs b/moe/src/surrogates.rs
index 64301f36..8ad5549f 100644
--- a/moe/src/surrogates.rs
+++ b/moe/src/surrogates.rs
@@ -5,7 +5,7 @@ use egobox_gp::{
     SparseGaussianProcess, SparseMethod, ThetaTuning,
 };
 use linfa::prelude::{Dataset, Fit};
-use ndarray::{Array1, Array2, ArrayView2};
+use ndarray::{Array1, Array2, ArrayView2, Axis};
 use paste::paste;
 
 #[cfg(feature = "serializable")]
@@ -46,11 +46,11 @@ pub trait GpSurrogate: std::fmt::Display + Sync + Send {
     fn dims(&self) -> (usize, usize);
     /// Predict output values at n points given as (n, xdim) matrix.
     #[deprecated(since = "0.17.0", note = "renamed predict")]
-    fn predict_values(&self, x: &ArrayView2<f64>) -> Result<Array2<f64>> {
+    fn predict_values(&self, x: &ArrayView2<f64>) -> Result<Array1<f64>> {
         self.predict(x)
     }
-    /// Predict output values at n points given as (n, xdim) matrix.
-    fn predict(&self, x: &ArrayView2<f64>) -> Result<Array2<f64>>;
+    /// Predict output values at n points given as a vector (n,)..
+    fn predict(&self, x: &ArrayView2<f64>) -> Result<Array1<f64>>;
     /// Predict variance values at n points given as (n, xdim) matrix.
     fn predict_var(&self, x: &ArrayView2<f64>) -> Result<Array2<f64>>;
     /// Save model in given file.
@@ -133,7 +133,7 @@ macro_rules! declare_surrogate {
                     y: &ArrayView2<f64>,
                 ) -> Result<Box<dyn FullGpSurrogate>> {
                     Ok(Box::new([<Gp $regr $corr Surrogate>](
-                        self.0.clone().fit(&Dataset::new(x.to_owned(), y.to_owned()))?,
+                        self.0.clone().fit(&Dataset::new(x.to_owned(), y.to_owned().remove_axis(Axis(1))))?,
                     )))
                 }
             }
@@ -150,7 +150,7 @@ macro_rules! declare_surrogate {
                 fn dims(&self) -> (usize, usize) {
                     self.0.dims()
                 }
-                fn predict(&self, x: &ArrayView2<f64>) -> Result<Array2<f64>> {
+                fn predict(&self, x: &ArrayView2<f64>) -> Result<Array1<f64>> {
                     Ok(self.0.predict(x)?)
                 }
                 fn predict_var(&self, x: &ArrayView2<f64>) -> Result<Array2<f64>> {
@@ -281,7 +281,7 @@ macro_rules! declare_sgp_surrogate {
                     y: &ArrayView2<f64>,
                 ) -> Result<Box<dyn FullGpSurrogate>> {
                     Ok(Box::new([<Sgp $corr Surrogate>](
-                        self.0.clone().fit(&Dataset::new(x.to_owned(), y.to_owned()))?,
+                        self.0.clone().fit(&Dataset::new(x.to_owned(), y.to_owned().remove_axis(Axis(1))))?,
                     )))
                 }
             }
@@ -308,7 +308,7 @@ macro_rules! declare_sgp_surrogate {
                 fn dims(&self) -> (usize, usize) {
                     self.0.dims()
                 }
-                fn predict(&self, x: &ArrayView2<f64>) -> Result<Array2<f64>> {
+                fn predict(&self, x: &ArrayView2<f64>) -> Result<Array1<f64>> {
                     Ok(self.0.predict(x)?)
                 }
                 fn predict_var(&self, x: &ArrayView2<f64>) -> Result<Array2<f64>> {
@@ -451,8 +451,8 @@ mod tests {
     use ndarray_linalg::Norm;
     use ndarray_stats::DeviationExt;
 
-    fn xsinx(x: &Array2<f64>) -> Array2<f64> {
-        (x - 3.5) * ((x - 3.5) / std::f64::consts::PI).mapv(|v| v.sin())
+    fn xsinx(x: &Array2<f64>) -> Array1<f64> {
+        ((x - 3.5) * ((x - 3.5) / std::f64::consts::PI).mapv(|v| v.sin())).remove_axis(Axis(1))
     }
 
     #[test]
@@ -461,7 +461,7 @@ mod tests {
         let xt = Lhs::new(&xlimits).sample(10);
         let yt = xsinx(&xt);
         let gp = make_surrogate_params!(Constant, SquaredExponential)
-            .train(&xt.view(), &yt.view())
+            .train(&xt.view(), &yt.insert_axis(Axis(1)).view())
             .expect("GP fit error");
         gp.save("target/tests/save_gp.json", GpFileFormat::Json)
             .expect("GP not saved");
diff --git a/python/egobox/tests/test_gpmix.py b/python/egobox/tests/test_gpmix.py
index 76cc7dbb..c57c2f5a 100644
--- a/python/egobox/tests/test_gpmix.py
+++ b/python/egobox/tests/test_gpmix.py
@@ -25,8 +25,7 @@ def setUp(self):
         self.xt = np.array([[0.0, 1.0, 2.0, 3.0, 4.0]]).T
         self.yt = np.array([[0.0, 1.0, 1.5, 0.9, 1.0]]).T
 
-        gpmix = egx.GpMix()  # or egx.Gpx.builder()
-        self.gpx = gpmix.fit(self.xt, self.yt)
+        self.gpx = egx.Gpx.builder().fit(self.xt, self.yt)
 
     def test_gpx_kriging(self):
         gpx = self.gpx
@@ -83,7 +82,7 @@ def test_training_params(self):
         self.assertEqual(self.gpx.dims(), (1, 1))
         (xdata, ydata) = self.gpx.training_data()
         np.testing.assert_array_equal(xdata, self.xt)
-        np.testing.assert_array_equal(ydata, self.yt)
+        np.testing.assert_array_equal(np.atleast_2d(ydata).T, self.yt)
 
     def test_kpls_griewank(self):
         lb = -600
@@ -127,6 +126,12 @@ def test_multi_outputs_exception(self):
         with self.assertRaises(BaseException):
             egx.Gpx.builder().fit(self.xt, self.yt)
 
+    def test_1d_training_data(self):
+        self.xt1 = np.array([0.0, 1.0, 2.0, 3.0, 4.0])
+        self.yt1 = np.array([0.0, 1.0, 1.5, 0.9, 1.0])
+
+        self.gpx = egx.Gpx.builder().fit(self.xt1, self.yt1)
+
 
 if __name__ == "__main__":
     unittest.main()
diff --git a/python/egobox/tests/test_sgpmix.py b/python/egobox/tests/test_sgpmix.py
index a838f298..91054385 100644
--- a/python/egobox/tests/test_sgpmix.py
+++ b/python/egobox/tests/test_sgpmix.py
@@ -16,68 +16,53 @@ def f_obj(x):
 
 
 class TestSgp(unittest.TestCase):
-    def test_sgp(self):
+    def setUp(self):
         # random generator for reproducibility
-        rng = np.random.RandomState(0)
+        self.rng = np.random.RandomState(0)
 
         # Generate training data
-        nt = 200
+        self.nt = 200
         # Variance of the gaussian noise on our trainingg data
         eta2 = [0.01]
-        gaussian_noise = rng.normal(loc=0.0, scale=np.sqrt(eta2), size=(nt, 1))
-        xt = 2 * rng.rand(nt, 1) - 1
-        yt = f_obj(xt) + gaussian_noise
+        gaussian_noise = self.rng.normal(
+            loc=0.0, scale=np.sqrt(eta2), size=(self.nt, 1)
+        )
+        self.xt = 2 * self.rng.rand(self.nt, 1) - 1
+        self.yt = f_obj(self.xt) + gaussian_noise
 
         # Pick inducing points randomly in training data
-        n_inducing = 30
-        random_idx = rng.permutation(nt)[:n_inducing]
-        Z = xt[random_idx].copy()
+        self.n_inducing = 30
+
+    def test_sgp(self):
+        random_idx = self.rng.permutation(self.nt)[: self.n_inducing]
+        Z = self.xt[random_idx].copy()
 
         start = time.time()
-        sgp = egx.SparseGpMix(z=Z).fit(xt, yt)
+        sgp = egx.SparseGpMix(z=Z).fit(self.xt, self.yt)
         elapsed = time.time() - start
         print(elapsed)
         sgp.save("sgp.json")
 
     def test_sgp_random(self):
-        # random generator for reproducibility
-        rng = np.random.RandomState(0)
-
-        # Generate training data
-        nt = 200
-        # Variance of the gaussian noise on our trainingg data
-        eta2 = [0.01]
-        gaussian_noise = rng.normal(loc=0.0, scale=np.sqrt(eta2), size=(nt, 1))
-        xt = 2 * rng.rand(nt, 1) - 1
-        yt = f_obj(xt) + gaussian_noise
-
-        # Pick inducing points randomly in training data
-        n_inducing = 30
-
         start = time.time()
-        sgp = egx.SparseGpMix(nz=n_inducing, seed=0).fit(xt, yt)
+        sgp = egx.SparseGpMix(nz=self.n_inducing, seed=0).fit(self.xt, self.yt)
         elapsed = time.time() - start
         print(elapsed)
         print(sgp)
 
     def test_sgp_multi_outputs_exception(self):
-        # random generator for reproducibility
-        rng = np.random.RandomState(0)
+        yt = np.hstack((self.yt, self.yt))
 
-        # Generate training data
-        nt = 200
-        # Variance of the gaussian noise on our trainingg data
-        eta2 = [0.01]
-        gaussian_noise = rng.normal(loc=0.0, scale=np.sqrt(eta2), size=(nt, 1))
-        xt = 2 * rng.rand(nt, 1) - 1
-        yt = f_obj(xt) + gaussian_noise
-        yt = np.hstack((yt, yt))
+        with self.assertRaises(BaseException):
+            egx.SparseGpx.builder(nz=self.n_inducing, seed=0).fit(self.xt, yt)
 
-        # Pick inducing points randomly in training data
-        n_inducing = 30
+    def test_1d_training_data(self):
+        self.xt1 = np.array([0.0, 1.0, 2.0, 3.0, 4.0])
+        self.yt1 = np.array([0.0, 1.0, 1.5, 0.9, 1.0])
 
-        with self.assertRaises(BaseException):
-            egx.SparseGpMix(nz=n_inducing, seed=0).fit(xt, yt)
+        self.sgpx = egx.SparseGpx.builder(nz=self.n_inducing, seed=0).fit(
+            self.xt, self.yt
+        )
 
 
 if __name__ == "__main__":
diff --git a/src/gp_mix.rs b/src/gp_mix.rs
index c84e403e..2f10caf4 100644
--- a/src/gp_mix.rs
+++ b/src/gp_mix.rs
@@ -17,9 +17,10 @@ use egobox_moe::{Clustered, MixtureGpSurrogate, ThetaTuning};
 #[allow(unused_imports)] // Avoid linting problem
 use egobox_moe::{GpMixture, GpSurrogate, GpSurrogateExt};
 use linfa::{traits::Fit, Dataset};
-use ndarray::{Array1, Array2, Zip};
+use log::error;
+use ndarray::{Array1, Array2, Axis, Ix1, Ix2, Zip};
 use ndarray_rand::rand::SeedableRng;
-use numpy::{IntoPyArray, PyArray1, PyArray2, PyReadonlyArray2};
+use numpy::{IntoPyArray, PyArray1, PyArray2, PyReadonlyArray2, PyReadonlyArrayDyn};
 use pyo3::prelude::*;
 use rand_xoshiro::Xoshiro256Plus;
 
@@ -129,8 +130,38 @@ impl GpMix {
     /// Returns Gpx object
     ///     the fitted Gaussian process mixture  
     ///
-    fn fit(&mut self, py: Python, xt: PyReadonlyArray2<f64>, yt: PyReadonlyArray2<f64>) -> Gpx {
-        let dataset = Dataset::new(xt.as_array().to_owned(), yt.as_array().to_owned());
+    fn fit(&mut self, py: Python, xt: PyReadonlyArrayDyn<f64>, yt: PyReadonlyArrayDyn<f64>) -> Gpx {
+        let xt = xt.as_array();
+        let xt = match xt.to_owned().into_dimensionality::<Ix2>() {
+            Ok(xt) => xt,
+            Err(_) => match xt.into_dimensionality::<Ix1>() {
+                Ok(xt) => xt.insert_axis(Axis(1)).to_owned(),
+                _ => {
+                    error!("Training input has to be an [nsamples, nx] array");
+                    panic!("Bad training input data");
+                }
+            },
+        };
+
+        let yt = yt.as_array();
+        let yt = match yt.to_owned().into_dimensionality::<Ix1>() {
+            Ok(yt) => yt,
+            Err(_) => match yt.into_dimensionality::<Ix2>() {
+                Ok(yt) => {
+                    if yt.dim().1 == 1 {
+                        yt.to_owned().remove_axis(Axis(1))
+                    } else {
+                        error!("Training output has to be one dimensional");
+                        panic!("Bad training output data");
+                    }
+                }
+                Err(_) => {
+                    error!("Training output has to be one dimensional");
+                    panic!("Bad training output data");
+                }
+            },
+        };
+        let dataset = Dataset::new(xt, yt);
 
         let recomb = match self.recombination {
             Recombination::Hard => egobox_moe::Recombination::Hard,
@@ -155,7 +186,11 @@ impl GpMix {
                 bounds: bounds.iter().map(|v| (v[0], v[1])).collect(),
             }
         }
-        let theta_tunings = vec![theta_tuning; self.n_clusters];
+        let theta_tunings = if self.n_clusters > 0 {
+            vec![theta_tuning; self.n_clusters]
+        } else {
+            vec![theta_tuning; 1] // used as default theta tuning for all experts
+        };
 
         if let Err(ctrlc::Error::MultipleHandlers) = ctrlc::set_handler(|| std::process::exit(2)) {
             // ignore multiple handlers error
@@ -284,6 +319,7 @@ impl Gpx {
         self.0
             .predict(&x.as_array())
             .unwrap()
+            .insert_axis(Axis(1))
             .into_pyarray_bound(py)
     }
 
@@ -383,12 +419,12 @@ impl Gpx {
     /// Get the nt training data points used to fit the surrogate
     ///
     /// Returns
-    ///     the couple (ndarray[nt, nx], ndarray[nt, ny])
+    ///     the couple (ndarray[nt, nx], ndarray[nt,])
     ///
     fn training_data<'py>(
         &self,
         py: Python<'py>,
-    ) -> (Bound<'py, PyArray2<f64>>, Bound<'py, PyArray2<f64>>) {
+    ) -> (Bound<'py, PyArray2<f64>>, Bound<'py, PyArray1<f64>>) {
         let (xdata, ydata) = self.0.training_data();
         (
             xdata.to_owned().into_pyarray_bound(py),
diff --git a/src/sparse_gp_mix.rs b/src/sparse_gp_mix.rs
index 5fca3e9a..28bfe3c3 100644
--- a/src/sparse_gp_mix.rs
+++ b/src/sparse_gp_mix.rs
@@ -16,7 +16,8 @@ use egobox_moe::{
     Clustered, GpMixture, GpSurrogate, GpType, Inducings, MixtureGpSurrogate, ThetaTuning,
 };
 use linfa::{traits::Fit, Dataset};
-use ndarray::{Array1, Array2, Zip};
+use log::error;
+use ndarray::{Array1, Array2, Axis, Ix1, Ix2, Zip};
 use ndarray_rand::rand::SeedableRng;
 use numpy::{IntoPyArray, PyArray1, PyArray2, PyReadonlyArray2};
 use pyo3::prelude::*;
@@ -124,7 +125,38 @@ impl SparseGpMix {
         xt: PyReadonlyArray2<f64>,
         yt: PyReadonlyArray2<f64>,
     ) -> SparseGpx {
-        let dataset = Dataset::new(xt.as_array().to_owned(), yt.as_array().to_owned());
+        let xt = xt.as_array();
+        let xt = match xt.to_owned().into_dimensionality::<Ix2>() {
+            Ok(xt) => xt,
+            Err(_) => match xt.into_dimensionality::<Ix1>() {
+                Ok(xt) => xt.insert_axis(Axis(1)).to_owned(),
+                _ => {
+                    error!("Training input has to be an [nsamples, nx] array");
+                    panic!("Bad training input data");
+                }
+            },
+        };
+
+        let yt = yt.as_array();
+        let yt = match yt.to_owned().into_dimensionality::<Ix1>() {
+            Ok(yt) => yt,
+            Err(_) => match yt.into_dimensionality::<Ix2>() {
+                Ok(yt) => {
+                    if yt.dim().1 == 1 {
+                        yt.to_owned().remove_axis(Axis(1))
+                    } else {
+                        error!("Training output has to be one dimensional");
+                        panic!("Bad training output data");
+                    }
+                }
+                Err(_) => {
+                    error!("Training output has to be one dimensional");
+                    panic!("Bad training output data");
+                }
+            },
+        };
+
+        let dataset = Dataset::new(xt, yt);
 
         let rng = if let Some(seed) = self.seed {
             Xoshiro256Plus::seed_from_u64(seed)
@@ -279,9 +311,9 @@ impl SparseGpx {
     ///         input values
     ///
     /// Returns
-    ///     the output values at nsamples x points (array[nsamples, 1])
+    ///     the output values at nsamples x points (array[nsamples])
     ///
-    fn predict<'py>(&self, py: Python<'py>, x: PyReadonlyArray2<f64>) -> Bound<'py, PyArray2<f64>> {
+    fn predict<'py>(&self, py: Python<'py>, x: PyReadonlyArray2<f64>) -> Bound<'py, PyArray1<f64>> {
         self.0
             .predict(&x.as_array())
             .unwrap()