Taming the monster: A fast and simple algorithm for contextual bandits

31st International Conference on Machine Learning, ICML 2014

Volumn 5, Issue , 2014, Pages 3611-3619

  Agarwal, Alekh ^a   Hsu, Daniel ^b   Kale, Satyen ^c   Langford, John ^a   Li, Lihong ^a   Schapire, Robert E ^d  

^a MICROSOFT RESEARCH   (United States)

^b Och Spine at New York Presbyterian Hospitals   (United States)

^c YAHOO RESEARCH   (United States)

^d PRINCETON UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; LEARNING SYSTEMS;

CONTEXTUAL BANDITS; COST-SENSITIVE CLASSIFICATION; LEARNING PROBLEM; OPTIMAL REGRET; PROOF OF CONCEPT; SIMPLE ALGORITHM; STATISTICAL PERFORMANCE;

LEARNING ALGORITHMS;

EID: 84919787147     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (19)

1. Agarwal, Alekh, Hsu, Daniel, Kale, Satyen, Langford, John, Li, Lihong, and Schapire, Robert E. Taming the monster: A fast and simple algorithm for contextual bandits. CoRR, abs/1402.0555, 2014.
2. Auer, Peter. Using confidence bounds for exploitation-exploration trade-offs. Journal of Machine Learning Research, 3:397-422, 2002.
3. Auer, Peter, Cesa-Bianchi, Nicolo, Freund, Yoav, and Schapire, Robert E. The nonstochastic multiarmed bandit problem. SIAM Journal of Computing, 32(l):48-77, 2002.
4. Beygelzimer, Alina and Langford, John. The offset tree for learning with partial labels. In KDD, 2009.
5. Beygelzimer, AUna, Langford, John, Li, Lihong, Reyzin, Lev, and Schapire, Robert E. Contextual bandit algorithms with supervised learning guarantees. In AISTATS, 2011.
6. Blum, Avrim, Kalai, Adam, and Langford, John. Beating the holdout: Bounds for k-fold and progressive cross-validation. In COLT, 1999.
7. Chapelle, Olivier and Li, Lihong. An empirical evaluation of Thompson sampling. In NIPS, 2011.
8. Chu, Wei, Li, Lihong, Reyzin, Lev, and Schapire, Robert E. Contextual bandits with linear payoff functions. In AISTATS, 2011.
9. Dudik, Miroslav, Hsu, Daniel, Kale, Satyen, Karampatzi-akis, Nikos, Langford, John, Reyzin, Lev, and Zhang, Tong. Efficient optimal learning for contextual bandits. In UAI, 2011a.
10. Dudik, Miroslav, Langford, John, and Li, Lihong. Doubly robust policy evaluation and learning. In ICML, 2011b.
11. Helmbold, David P. and Schapire, Robert E. Predicting neariy as well as the best pruning of a decision tree. Machine Learning, 27(l):51-68, 1997.
12. Langford, John. Interactive machine learning, January 2014. URL http://hunch.net/-jl/projects/interactive/index.html.
13. Langford, John and Zhang, Tong. The epoch-greedy algorithm for contextual multi-armed bandits. In NIPS, 2007.
14. Lewis, David D, Yang, Yiming, Rose, Tony G, and Li, Fan. Rev I: A new benchmark collection for text categorization research. The Journal of Machine Learning Research, 5:361-397, 2004.
15. Li, Lihong. Generalized Thompson sampling for contextual bandits. CoRR, abs/1310.7163, 2013.
16. Li, Lihong, Chu, Wei, Langford, John, and Schapire, Robert E. A contextual-bandit approach to personalized news article recommendation. In WWW, 2010.
17. McMahan, H. Brendan and Streeter, Matthew. Tighter bounds for multi-armed bandits with expert advice. In COLT, 2009.
18. Sutton, Richard S. and Barto, Andrew G. Reinforcement learning, an introduction. MIT Press, 1998.
19. Thompson, William R. On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika, 25(3-4):285-294, 1933.