Flash-SD-KDE: Accelerating SD-KDE with Tensor Cores
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912896526581760 |
|---|---|
| author | Epstein, Elliot L. Dwaraknath, Rajat Vadiraj Winnicki, John |
| author_facet | Epstein, Elliot L. Dwaraknath, Rajat Vadiraj Winnicki, John |
| contents | Score-debiased kernel density estimation (SD-KDE) achieves improved asymptotic convergence rates over classical KDE, but its use of an empirical score has made it significantly slower in practice. We show that by re-ordering the SD-KDE computation to expose matrix-multiplication structure, Tensor Cores can be used to accelerate the GPU implementation. On a 32k-sample 16-dimensional problem, our approach runs up to $47\times$ faster than a strong SD-KDE GPU baseline and $3{,}300\times$ faster than scikit-learn's KDE. On a larger 1M-sample 16-dimensional task evaluated on 131k queries, Flash-SD-KDE completes in $2.3$ s on a single GPU, making score-debiased density estimation practical at previously infeasible scales. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_10378 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Flash-SD-KDE: Accelerating SD-KDE with Tensor Cores Epstein, Elliot L. Dwaraknath, Rajat Vadiraj Winnicki, John Distributed, Parallel, and Cluster Computing Machine Learning I.2.0 Score-debiased kernel density estimation (SD-KDE) achieves improved asymptotic convergence rates over classical KDE, but its use of an empirical score has made it significantly slower in practice. We show that by re-ordering the SD-KDE computation to expose matrix-multiplication structure, Tensor Cores can be used to accelerate the GPU implementation. On a 32k-sample 16-dimensional problem, our approach runs up to $47\times$ faster than a strong SD-KDE GPU baseline and $3{,}300\times$ faster than scikit-learn's KDE. On a larger 1M-sample 16-dimensional task evaluated on 131k queries, Flash-SD-KDE completes in $2.3$ s on a single GPU, making score-debiased density estimation practical at previously infeasible scales. |
| title | Flash-SD-KDE: Accelerating SD-KDE with Tensor Cores |
| topic | Distributed, Parallel, and Cluster Computing Machine Learning I.2.0 |
| url | https://arxiv.org/abs/2602.10378 |