Conditional gradient methods via stochastic path-integrated differential estimator
Name
yurtsever19b.pdf
Description
Published version
Size
271.86 KB
Format
Adobe PDF
Checksum (MD5)
6c2f7f6020e924b279dbcae3d9cc9626
Author(s)
Sra, Suvrit
Date Issued
June 2019
Journal
Proceedings of Machine Learning Research
Publisher
International Machine Learning Society
Citation
Yurtsever, Alp et al. “Conditional gradient methods via stochastic path-integrated differential estimator.” Paper in the Proceedings of Machine Learning Research, 97, 36th International Conference on Machine Learning ICML 2019, Long Beach, California, 9-15 June 2019, American Society of Mechanical Engineers: 7282-7291 © 2019 The Author(s)
Version
Final published version
Abstract
We propose a class of novel variance-reduced stochastic conditional gradient methods. By adopting the recent stochastic path-integrated differential estimator technique (SPIDER) of Fang ct al. (2018) for the classical Frank-Wolfe (FW) method, we introduce SPIDER-FW for finite-sum minimization as well as the more general expectation minimization problems. SPIDER-FW enjoys superior complexity guarantees in the non-convex setting, while matching the best known FW variants in the convex case. We also extend our framework à la conditional gradient sliding (CGS) of Lan & Zhou (2016), and propose SPIDER-CGS.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
