diff --git a/cpp/daal/src/algorithms/kmeans/kmeans_plusplus_init_impl.i b/cpp/daal/src/algorithms/kmeans/kmeans_plusplus_init_impl.i
index 158a906d572..a89d3f0bfea 100644
--- a/cpp/daal/src/algorithms/kmeans/kmeans_plusplus_init_impl.i
+++ b/cpp/daal/src/algorithms/kmeans/kmeans_plusplus_init_impl.i
@@ -287,20 +287,29 @@ public:
         return _csr->releaseSparseBlock(block);
     }
 
+    //calculate distance from current trial center to the rows in the block and update min distance
     algorithmFPType updateMinDistForITrials(algorithmFPType * const pDistSq, size_t iTrials, size_t nRowsToProcess,
                                             const algorithmFPType * const pData, const size_t * const colIdx, const size_t * const rowIdx,
                                             const algorithmFPType * const pLastAddedCenter, const algorithmFPType * const aWeights,
                                             const algorithmFPType * const pDistSqBest)
     {
-        algorithmFPType sumOfDist2 = algorithmFPType(0);
-        size_t csrCursor           = 0u;
+        algorithmFPType sumOfDist2            = algorithmFPType(0);
+        size_t csrCursor                      = 0u;
+        algorithmFPType pLastAddedCenterSumSq = algorithmFPType(0.);
+        for (size_t iCol = 0u; iCol < dim; iCol++)
+        {
+            pLastAddedCenterSumSq += pLastAddedCenter[iCol] * pLastAddedCenter[iCol];
+        }
+
         for (size_t iRow = 0u; iRow < nRowsToProcess; iRow++)
         {
-            algorithmFPType dist2 = algorithmFPType(0);
+            algorithmFPType dist2 = pLastAddedCenterSumSq;
             const size_t nValues  = rowIdx[iRow + 1] - rowIdx[iRow];
+
+            //distance from the lastAddedCenter to the current row, dist2 = x^2 + y^2 - 2xy
             for (size_t i = 0u; i < nValues; i++, csrCursor++)
             {
-                dist2 += (pData[csrCursor] - pLastAddedCenter[colIdx[csrCursor] - 1]) * (pData[csrCursor] - pLastAddedCenter[colIdx[csrCursor] - 1]);
+                dist2 += pData[csrCursor] * pData[csrCursor] - 2 * pData[csrCursor] * pLastAddedCenter[colIdx[csrCursor] - 1];
             }
             if (aWeights)
             {
diff --git a/cpp/oneapi/dal/algo/kmeans_init/backend/cpu/compute_kernel_dense.cpp b/cpp/oneapi/dal/algo/kmeans_init/backend/cpu/compute_kernel_dense.cpp
index b4347518dc1..3a58e13a566 100644
--- a/cpp/oneapi/dal/algo/kmeans_init/backend/cpu/compute_kernel_dense.cpp
+++ b/cpp/oneapi/dal/algo/kmeans_init/backend/cpu/compute_kernel_dense.cpp
@@ -14,6 +14,8 @@
 * limitations under the License.
 *******************************************************************************/
 
+#include <cmath>
+
 #include <daal/src/algorithms/kmeans/kmeans_init_kernel.h>
 
 #include "oneapi/dal/algo/kmeans_init/backend/cpu/compute_kernel.hpp"
@@ -43,9 +45,18 @@ static compute_result<Task> call_daal_kernel(const context_cpu& ctx,
     const std::int64_t column_count = data.get_column_count();
     const std::int64_t cluster_count = desc.get_cluster_count();
 
+    //number of trials to pick each centroid from, 2 + int(ln(cluster_count)) works better than vanilla kmeans++
+    //https://github.com/scikit-learn/scikit-learn/blob/a63b021310ba13ea39ad3555f550d8aeec3002c5/sklearn/cluster/_kmeans.py#L108
+    std::int64_t trial_count = desc.get_local_trials_count();
+    if (trial_count == -1) {
+        const auto additional = std::log(cluster_count);
+        trial_count = 2 + std::int64_t(additional);
+    }
+
     daal_kmeans_init::Parameter par(dal::detail::integral_cast<std::size_t>(cluster_count),
                                     0,
                                     dal::detail::integral_cast<std::size_t>(desc.get_seed()));
+    par.nTrials = trial_count;
 
     const auto daal_data = interop::convert_to_daal_table<Float>(data);
     const std::size_t len_input = 1;