论文标题
通过GPU加速使UMAP更接近光速
Bringing UMAP Closer to the Speed of Light with GPU Acceleration
论文作者
论文摘要
统一的歧管近似和投影（UMAP）算法因其易用性，结果质量以及对探索性，无监督，监督和半监督学习的支持而广受欢迎。尽管许多算法可以以简单而直接的方式移植到GPU，但这种努力导致UMAP的效率低下和不准确的版本。我们展示了许多技术，可用于制造更快，更忠实的GPU版本的UMAP，并在实践中获得高达100倍的加速度。这些设计选择/课程中的许多都是通用，可以告知其他图形和流形学习算法使用GPU的转换。我们的实施已作为开源Rapids cuml库（https://github.com/rapidsai/cuml）的一部分公开提供。
The Uniform Manifold Approximation and Projection (UMAP) algorithm has become widely popular for its ease of use, quality of results, and support for exploratory, unsupervised, supervised, and semi-supervised learning. While many algorithms can be ported to a GPU in a simple and direct fashion, such efforts have resulted in inefficient and inaccurate versions of UMAP. We show a number of techniques that can be used to make a faster and more faithful GPU version of UMAP, and obtain speedups of up to 100x in practice. Many of these design choices/lessons are general purpose and may inform the conversion of other graph and manifold learning algorithms to use GPUs. Our implementation has been made publicly available as part of the open source RAPIDS cuML library (https://github.com/rapidsai/cuml).
