用张量核心加速得分去偏核密度估计，大幅提升计算效率。
Flash-SD-KDE: Accelerating SD-KDE with Tensor Cores
- 重排计算顺序暴露矩阵乘法结构，适配GPU张量核心
- 32k样本16维任务快47倍，百万样本任务仅需2.3秒
- 适合需要大规模密度估计的科研与工程场景
得分去偏核密度估计（SD-KDE）相较于经典KDE具有更优的渐近收敛率，但因使用经验得分导致实际计算极慢。本文通过重新组织SD-KDE计算以暴露矩阵乘法结构，使张量核心得以应用，显著加速GPU实现。在32,000样本、16维问题上，本方法比强基线SD-KDE GPU版本快达47倍，比scikit-learn的KDE快3,300倍；在包含100万样本、131,000个查询的大规模任务中，单卡仅耗时2.3秒，使此前不可行的大规模得分去偏密度估计成为可能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。