Beyond the regret minimization barrier: Optimal algorithms for stochastic strongly-convex optimization

Journal of Machine Learning Research

Volumn 15, Issue , 2014, Pages 2489-2512

  Hazan, Elad ^a   Kale, Satyen ^b  

^a TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

^b YAHOO RESEARCH   (United States)

Author keywords

Convex optimization; Online Learning; Regret minimization; Stochastic gradient descent

Indexed keywords

CONVEX OPTIMIZATION; OPTIMIZATION; STOCHASTIC MODELS; STOCHASTIC SYSTEMS;

APPROXIMATE SOLUTION; ONLINE CONVEX OPTIMIZATIONS; ONLINE LEARNING; OPTIMAL ALGORITHM; OPTIMIZATION ALGORITHMS; RATE OF CONVERGENCE; REGRET MINIMIZATION; STOCHASTIC GRADIENT DESCENT;

ALGORITHMS;

EID: 84907359690     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Article

References (22)

1. Jacob Abernethy, Alekh Agarwal, Peter L. Bartlett, and Alexander Rakhlin. A stochastic view of optimal regret through minimax duality. In COLT, 2009.
2. Alekh Agarwal, Peter L. Bartlett, Pradeep D. Ravikumar, and Martin J. Wainwright. Information-theoretic lower bounds on the oracle complexity of stochastic convex optimization. IEEE Transactions on Information Theory, 58(5):3235-3249, 2012.
3. Peter L. Bartlett, Elad Hazan, and Alexander Rakhlin. Adaptive online gradient descent. In NIPS, 2007.
4. Dimitri P. Bertsekas. Nonlinear Programming. Athena Scientific, 2nd edition, September 1999. ISBN 1886529000.
5. Jonathan M. Borwein and Adrian S. Lewis. Convex Analysis and Nonlinear Optimization. Springer, 2006.
6. Leon Bottou and Olivier Bousquet. The tradeoffs of large scale learning. In NIPS, 2007.
7. Lev M. Bregman. The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming. USSR Computational Mathematics and Mathematical Physics, 7:200-217, 1967.
8. Nicolo Cesa-Bianchi and Gabor Lugosi. Prediction, Learning, and Games. Cambridge University Press, 2006.
9. Saeed Ghadimi and Guanghui Lan. Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization. In Optimization Online, 2010. URL http://www.optimization-online.org/DB-HTML/2010/ 07/2669.html.
10. Elad Hazan and Satyen Kale. An optimal algorithm for stochastic strongly-convex optimization. In arXiv:1006.2425v1, June 2010. URL http://arxiv.org/abs/1006.2425.
11. Elad Hazan and Satyen Kale. Beyond the regret minimization barrier: an optimal algorithm for stochastic strongly-convex optimization. In COLT, 2011.
12. Elad Hazan, Amit Agarwal, and Satyen Kale. Logarithmic regret algorithms for online convex optimization. Machine Learning, 69(2-3):169-192, 2007.
13. Anatoli Juditsky and Yuri Nesterov. Primal-dual subgradient methods for minimizing uniformly convex functions. August 2010. URL http://hal.archives- ouvertes.fr/docs/00/50/89/33/PDF/Strong-hal.pdf.
14. Guanghui Lan, Arkadi Nemirovski, and Alexander Shapiro. Validation analysis of mirror descent stochastic approximation method. Math. Program., 134(2):425-458, 2012.
15. Arkadi S. Nemirovski and David B. Yudin. Problem Complexity and Method Eficiency in Optimization. John Wiley UK/USA, 1983.
16. Erik Ordentlich and Thomas M. Cover. The cost of achieving the best portfolio in hindsight. Mathematics of Operations Research, 23:960-982, November 1998.
17. Alexander Rakhlin, Ohad Shamir, and Karthik Sridharan. Making gradient descent optimal for strongly convex stochastic optimization. In ICML, 2012.
18. Shai Shalev-Shwartz and Nathan Srebro. SVM optimization: inverse dependence on training set size. In ICML, 2008.
19. Shai Shalev-Shwartz, Ohad Shamir, Karthik Sridharan, and Nati Srebro. Stochastic convex optimization. In COLT, 2009.
20. Ohad Shamir and Tong Zhang. Stochastic gradient descent for non-smooth optimization: Convergence results and optimal averaging schemes. In ICML, 2013.
21. Eiji Takimoto and Manfred K. Warmuth. The minimax strategy for Gaussian density estimation. In COLT, 2000.
22. Martin Zinkevich. Online convex programming and generalized in finitesimal gradient ascent. In ICML, 2003.