Abstract | ||
---|---|---|
We study the statistical and computational aspects of kernel principal component analysis using random Fourier features and show that under mild assumptions, $O(sqrt{n} log n)$ features suffices to achieve $O(1/epsilon^2)$ sample complexity. Furthermore, we give a memory efficient streaming algorithm based on classical Ojau0027s algorithm that achieves this rate |
Year | Venue | Keywords |
---|---|---|
2018 | NeurIPS | sample complexity,kernel principal component analysis,kernel pca,learning from demonstration |
Field | DocType | Citations |
Binary logarithm,Mathematical optimization,Streaming algorithm,Computer science,Algorithm,Fourier transform,Kernel principal component analysis,Tilde,Sample complexity | Conference | 0 |
PageRank | References | Authors |
0.34 | 12 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Enayat Ullah | 1 | 0 | 2.37 |
Poorya Mianjy | 2 | 18 | 4.40 |
Teodor Marinov | 3 | 7 | 3.54 |
R. Arora | 4 | 489 | 35.97 |