NeurIPS 2017poster45 citations

Stochastic Approximation for Canonical Correlation Analysis

Raman Arora, Teodor Vanislavov Marinov, Poorya Mianjy, Nati Srebro

Abstract

We propose novel first-order stochastic approximation algorithms for canonical correlation analysis (CCA). Algorithms presented are instances of inexact matrix stochastic gradient (MSG) and inexact matrix exponentiated gradient (MEG), and achieve $\epsilon$-suboptimality in the population objective in $\operatorname{poly}(\frac{1}{\epsilon})$ iterations. We also consider practical variants of the proposed algorithms and compare them with other methods for CCA both theoretically and empirically.

BibTeX
@inproceedings{NIPS2017_c30fb4dc,
 author = {Arora, Raman and Marinov, Teodor Vanislavov and Mianjy, Poorya and Srebro, Nati},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {I. Guyon and U. Von Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {Stochastic Approximation for Canonical Correlation Analysis},
 url = {https://proceedings.neurips.cc/paper_files/paper/2017/file/c30fb4dc55d801fc7473840b5b161dfa-Paper.pdf},
 volume = {30},
 year = {2017}
}
Stochastic Approximation for Canonical Correlation Analysis · NeurIPS 2017