NeurIPS 2019oral34 citations

Exponentially convergent stochastic k-PCA without variance reduction

Cheng Tang

Abstract

We present Matrix Krasulina, an algorithm for online k-PCA, by gen- eralizing the classic Krasulina’s method (Krasulina, 1969) from vector to matrix case. We show, both theoretically and empirically, that the algorithm naturally adapts to data low-rankness and converges exponentially fast to the ground-truth principal subspace. Notably, our result suggests that despite various recent efforts to accelerate the convergence of stochastic-gradient based methods by adding a O(n)-time variance reduction step, for the k- PCA problem, a truly online SGD variant suffices to achieve exponential convergence on intrinsically low-rank data.

BibTeX
@inproceedings{NEURIPS2019_38faae06,
 author = {Tang, Cheng},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {Exponentially convergent stochastic k-PCA without variance reduction},
 url = {https://proceedings.neurips.cc/paper_files/paper/2019/file/38faae069a1371784081ea9ad9b279d0-Paper.pdf},
 volume = {32},
 year = {2019}
}
Exponentially convergent stochastic k-PCA without variance reduction · NeurIPS 2019