feature: add noise_variance computation on oneDAL side #3101
Conversation
|
/intelci: run |
Alexandr-Solovev
requested review from
Alexsandruss,
KateBlueSky,
avolkov-intel,
david-cortes-intel,
ethanglaser,
icfaust and
maria-Petrova
as code owners
| // SYEVR branch | ||
| // In this case, we compute only nComponents eigenvectors and then sort them in descending order | ||
| // inside the 'computeEigenvectorsInplaceSyevr' function | ||
| if (nComponents < nFeatures) |
There was a problem hiding this comment.
Could it also limit the components by the number of rows in the data by this point? Is that info available here?
| eigenvalues[i] = temp_eigenvalues[idx]; | ||
| for (size_t j = 0; j < nFeatures; ++j) | ||
| { | ||
| eigenvectors[j + i * nFeatures] = temp_eigenvectors[j + idx * nFeatures]; |
There was a problem hiding this comment.
There's a dedicated lapack function to reorder columns:
https://www.netlib.org/lapack/explore-3.2.1-html/dlapmt.f.html
Plus there's C++ 'reverse' for vectors:
https://en.cppreference.com/w/cpp/algorithm/reverse.html
|
|
||
| Float max_val = row[0]; | ||
| Float abs_max = std::abs(row[0]); | ||
| for (std::int64_t j = 1; j < column_count; j++) { |
There was a problem hiding this comment.
Would it perhaps be faster to use idamax from blas?
There was a problem hiding this comment.
I will add a todo for investigation. For now looks like makes the pr bigger
| auto explained_variances_ratio_ptr = explained_variances_ratio.get_mutable_data(); | ||
|
|
||
| Float sum = 0; | ||
| for (std::int64_t i = 0; i < column_count; ++i) { |
There was a problem hiding this comment.
Could oneDPL be used for this kind of things?
There was a problem hiding this comment.
I will add a todo mark, but may be done in next pr
| auto eigvals_ptr = eigenvalues.get_data(); | ||
| auto singular_values_ptr = singular_values.get_mutable_data(); | ||
|
|
||
| const Float factor = row_count - 1; |
There was a problem hiding this comment.
Why '-1' here? Wouldn't this make the result not meet the necessary property that
| auto compute_event = queue.submit([&](sycl::handler& h) { | ||
| h.depends_on(deps); | ||
| h.parallel_for(sycl::range<1>(component_count), [=](sycl::id<1> i) { | ||
| singular_values_ptr[i] = sycl::sqrt(factor * eigvals_ptr[i]); |
There was a problem hiding this comment.
syevr only generates results that are valid up to numerical tolerance. So a very small eigenvalue that should in theory be positive or zero could still end up as a very small negative number.
|
@Alexandr-Solovev please rebase |
|
/intelci: run |
|
/intelci: run |
|
/intelci: run |
5 participants
Changes Summary
Added
noise_variancecomputationImplemented calculation of noise variance as part of the PCA result options. This allows better estimation of the unexplained variance in the dataset.
Added
syevr-based eigen decomposition functionIntroduced a new function utilizing LAPACK's
syevrroutine to improve the performance of eigenvector and eigenvalue computations for symmetric matrices.PR should start as a draft, then move to ready for review state after CI is passed and all applicable checkboxes are closed.
This approach ensures that reviewers don't spend extra time asking for regular requirements.
You can remove a checkbox as not applicable only if it doesn't relate to this PR in any way.
For example, PR with docs update doesn't require checkboxes for performance while PR with any change in actual code should have checkboxes and justify how this code change is expected to affect performance (or justification should be self-evident).
Checklist to comply with before moving PR from draft:
PR completeness and readability
Testing
Performance