| ▲ | Flash-KMeans: Fast and Memory-Efficient Exact K-Means(arxiv.org) |
| 82 points by matt_d 3 days ago | 4 comments |
| |
|
| ▲ | wood_spirit 2 hours ago | parent | next [-] |
| Does this have corresponding speed ups or memory gains for normal CPUs too? Just thinking about all the cups of coffee that have been made and drunk while scikit-learn kmeans chugs through a notebook :) |
| |
| ▲ | snovv_crash 2 hours ago | parent [-] | | For CPU with bigger K you would put the centroids in a search tree, so take advantage of the sparsity, while a GPU would calculate the full NxK distance matrix. So from my understanding the bottleneck they are fixing doesn't show up on CPU. | | |
| ▲ | xavxav 2 hours ago | parent [-] | | search trees tend not to scale well to higher dimensions though, right? from what I've seen I had the impression that Yinyang k-means was the best way to take advantage of the sparsity. |
|
|
|
| ▲ | matrix2596 2 hours ago | parent | prev [-] |
| looks like flash attention concepts applied to kmeans, nice speedup results |
