Stochastic modified equations and adaptive stochastic gradient algorithms

Qianxiao Li, Cheng Tai, E. Weinan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

We develop the method of stochastic modified equations (SME), in which stochastic gradient algorithms are approximated in the weak sense by continuous-time stochastic differential equations. We exploit the continuous formulation together with optimal control theory to derive novel adaptive hyper-parameter adjustment policies. Our algorithms have competitive performance with the added benefit of being robust to varying models and datasets. This provides a general methodology for the analysis and design of stochastic gradient algorithms.

Original languageEnglish (US)
Title of host publication34th International Conference on Machine Learning, ICML 2017
PublisherInternational Machine Learning Society (IMLS)
Pages3306-3340
Number of pages35
ISBN (Electronic)9781510855144
StatePublished - Jan 1 2017
Event34th International Conference on Machine Learning, ICML 2017 - Sydney, Australia
Duration: Aug 6 2017Aug 11 2017

Publication series

Name34th International Conference on Machine Learning, ICML 2017
Volume5

Other

Other34th International Conference on Machine Learning, ICML 2017
CountryAustralia
CitySydney
Period8/6/178/11/17

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Human-Computer Interaction
  • Software

Fingerprint Dive into the research topics of 'Stochastic modified equations and adaptive stochastic gradient algorithms'. Together they form a unique fingerprint.

  • Cite this

    Li, Q., Tai, C., & Weinan, E. (2017). Stochastic modified equations and adaptive stochastic gradient algorithms. In 34th International Conference on Machine Learning, ICML 2017 (pp. 3306-3340). (34th International Conference on Machine Learning, ICML 2017; Vol. 5). International Machine Learning Society (IMLS).