Composite objective mirror descent

John C. Duchi, Shai Shalev-Shwartz, Yoram Singer, Ambuj Tewari

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

130 Scopus citations

Abstract

We present a new method for regularized convex optimization and analyze it under both online and stochastic optimization settings. In addition to unifying previously known firstorder algorithms, such as the projected gradient method, mirror descent, and forward-backward splitting, our method yields new analysis and algorithms. We also derive specific instantiations of our method for commonly used regularization functions, such as l1, mixed norm, and trace-norm.

Original languageEnglish (US)
Title of host publicationCOLT 2010 - The 23rd Conference on Learning Theory
Pages14-26
Number of pages13
StatePublished - Dec 1 2010
Externally publishedYes
Event23rd Conference on Learning Theory, COLT 2010 - Haifa, Israel
Duration: Jun 27 2010Jun 29 2010

Publication series

NameCOLT 2010 - The 23rd Conference on Learning Theory

Other

Other23rd Conference on Learning Theory, COLT 2010
CountryIsrael
CityHaifa
Period6/27/106/29/10

All Science Journal Classification (ASJC) codes

  • Education

Cite this

Duchi, J. C., Shalev-Shwartz, S., Singer, Y., & Tewari, A. (2010). Composite objective mirror descent. In COLT 2010 - The 23rd Conference on Learning Theory (pp. 14-26). (COLT 2010 - The 23rd Conference on Learning Theory).