Fast Rates for Empirical Risk Minimization of Strict Saddle Problems
Abstract
We derive bounds on the sample complexity of empirical risk minimization (ERM) in the context of minimizing non-convex risks that admit the strict saddle property. Recent progress in non-convex optimization has yielded efficient algorithms for minimizing such functions. Our results imply that these efficient algorithms are statistically stable and also generalize well. In particular, we derive fast rates which resemble the bounds that are often attained in the strongly convex setting. We specify our bounds to Principal Component Analysis and Independent Component Analysis. Our results and techniques may pave the way for statistical analyses of additional strict saddle problems.
Cite
Text
Gonen and Shalev-Shwartz. "Fast Rates for Empirical Risk Minimization of Strict Saddle Problems." Proceedings of the 2017 Conference on Learning Theory, 2017.Markdown
[Gonen and Shalev-Shwartz. "Fast Rates for Empirical Risk Minimization of Strict Saddle Problems." Proceedings of the 2017 Conference on Learning Theory, 2017.](https://mlanthology.org/colt/2017/gonen2017colt-fast/)BibTeX
@inproceedings{gonen2017colt-fast,
title = {{Fast Rates for Empirical Risk Minimization of Strict Saddle Problems}},
author = {Gonen, Alon and Shalev-Shwartz, Shai},
booktitle = {Proceedings of the 2017 Conference on Learning Theory},
year = {2017},
pages = {1043-1063},
volume = {65},
url = {https://mlanthology.org/colt/2017/gonen2017colt-fast/}
}