Follow-the-regularized-leader and mirror descent: Equivalence theorems and L1 regularization

Journal of Machine Learning Research

Volumn 15, Issue , 2011, Pages 525-533

  McMahan, H Brendan ^a  

^a GOOGLE INC   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CLOSED FORM; COMPOSITE MIRRORS; DATA SETS; EQUIVALENCE THEOREM; EXPERIMENTAL OBSERVATION; GRADIENT DESCENT; L1 REGULARIZATIONS; SUBGRADIENT;

ARTIFICIAL INTELLIGENCE; CONVEX OPTIMIZATION; MIRRORS;

ALGORITHMS;

EID: 84862284994     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Conference Paper

References (14)

1. Jacob Abernethy, Peter L. Bartlett, Alexander Rakhlin, and Ambuj Tewari. Optimal strategies and minimax lower bounds for online convex games. In COLT, 2008.
2. Peter Bartlett, Elad Hazan, and Alexander Rakhlin. Adaptive online gradient descent. Technical Report UCB/EECS-2007-82, EECS Department, University of California, Berkeley, Jun 2007.
3. Stephen Boyd and Lieven Vandenberghe. Convex Optimization. Cambridge University Press, New York, NY, USA, 2004. ISBN 0521833787.
4. Chih-Chung Chang and Chih-Jen Lin. LIBSVM data sets. http://www.csie.ntu. edu.tw/~cjlin/libsvmtools/datasets/, 2010.
5. Chuong B. Do, Quoc V. Le, and Chuan-Sheng Foo. Proximal regularization for online and batch learning. In ICML, 2009.
6. Mark Dredze. Multi-domain sentiment dataset (v2.0). http://www.cs.jhu. edu/~mdredze/datasets/sentiment/, 2010.
7. John Duchi and Yoram Singer. Efficient learning using forward-backward splitting. In NIPS, 2009.
8. John Duchi, Elad Hazan, and Yoram Singer. Adaptive subgradient methods for online learning and stochastic optimization. In COLT, 2010a.
9. John Duchi, Shai Shalev-Shwartz, Yoram Singer, and Ambuj Tewari. Composite objective mirror descent. In COLT, 2010b.
10. H. Brendan McMahan. A unified analysis of regularized dual averaging and composite mirror descent with implicit updates. Submitted, 2011.
11. H. Brendan McMahan and Matthew Streeter. Adaptive bound optimization for online convex optimization. In COLT, 2010.
12. Lin Xiao. Dual averaging method for regularized stochastic learning and online optimization. In NIPS, 2009.
13. Martin Zinkevich. Online convex programming and generalized infinitesimal gradient ascent. In ICML, 2003.
14. Martin Zinkevich. Theoretical guarantees for algorithms in multi-agent settings. PhD thesis, Pittsburgh, PA, USA, 2004.