| dc.contributor.author | Sra, Suvrit | |
| dc.date.accessioned | 2021-04-27T17:11:23Z | |
| dc.date.available | 2021-04-27T17:11:23Z | |
| dc.date.issued | 2019-06 | |
| dc.identifier.issn | 2640-3498 | |
| dc.identifier.uri | https://hdl.handle.net/1721.1/130530 | |
| dc.description.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. | en_US |
| dc.description.sponsorship | National Science Foundation (U.S.) (Grant 200021178865/1) | en_US |
| dc.description.sponsorship | National Science Foundation (U.S.). Career (Grant 1846088) | en_US |
| dc.language.iso | en | |
| dc.publisher | International Machine Learning Society | en_US |
| dc.rights | 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. | en_US |
| dc.source | Proceedings of Machine Learning Research | en_US |
| dc.title | Conditional gradient methods via stochastic path-integrated differential estimator | en_US |
| dc.type | Article | en_US |
| dc.identifier.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) | en_US |
| dc.contributor.department | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science | en_US |
| dc.relation.journal | Proceedings of Machine Learning Research | en_US |
| dc.eprint.version | Final published version | en_US |
| dc.type.uri | http://purl.org/eprint/type/ConferencePaper | en_US |
| eprint.status | http://purl.org/eprint/status/NonPeerReviewed | en_US |
| dc.date.updated | 2021-04-06T18:34:21Z | |
| dspace.orderedauthors | Yurtsever, A; Sra, S; Cevher, V | en_US |
| dspace.date.submission | 2021-04-06T18:34:22Z | |
| mit.journal.volume | 97 | en_US |
| mit.license | PUBLISHER_POLICY | |
| mit.metadata.status | Authority Work and Publication Information Needed | |
