Combinatorial partial monitoring game with linear feedback and its applications

31st International Conference on Machine Learning, ICML 2014

Volumn 3, Issue , 2014, Pages 2512-2537

  Lin, Tian ^a   Abrahao, Bruno ^b   Kleinberg, Robert ^b   Lui, John C S ^c   Chen, Wei ^d  

^a TSINGHUA UNIVERSITY   (China)

^b Cornell University ^*  (United States)

^c CHINESE UNIVERSITY OF HONG KONG   (Hong Kong)

^d MICROSOFT RESEARCH   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; E-LEARNING; LEARNING ALGORITHMS; LEARNING SYSTEMS; SOCIAL NETWORKING (ONLINE);

CONFIDENCE BOUNDS; EFFICIENT LEARNING; ITS APPLICATIONS; LIMITED FEEDBACK; MODEL AND ALGORITHMS; MULTI ARMED BANDIT; OFF-LINE OPTIMIZATION; ONLINE LEARNING;

COMBINATORIAL MATHEMATICS;

EID: 84919902752     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (17)

1. Antos, Andras, Bartok, Gabor, Pal, David, and Szepesvari, Csaba. Toward a classification of finite partial- monitoring games. Theoretical Computer Science, 2012.
2. Audibert, Jean-Yves and Bubeck, Sebastien. Minimax policies for adversarial and stochastic bandits. In COLT, 2009.
3. Auer, Peter, Cesa-Bianchi, Nicolo, and Fischer, Paul. Finite-time analysis of the multi armed bandit problem. Machine learning, 47(2-3):235-256, 2002.
4. Bartok, G., Zolghadr, N., and Szepesvari, Cs. An adaptive algorithm for finite stochastic partial monitoring (extended version). In ICML, pp. 1-20, June 2012.
5. Bartok, Gabor, Pal, David, and Szepesvari, Csaba. Minimax regret of finite partial-monitoring games in stochastic environments. Journal of Machine Learning Research-Proceedings Track, 19:133-154, 2011.
6. Bubeck, Sebastien and Cesa-Bianchi, Nicolo. Regret analysis of stochastic and non stochastic multi-armed bandit problems. Foundations and Trends in Machine Learning, 5(1):1-122, 2012.
7. Cesa-Bianchi, Nicolo and Lugosi, Gabor. Prediction, learning, and games. Cambridge University Press, 2006.
8. Cesa-Bianchi, Nicolo and Lugosi, Gabor. Combinatorial bandits. Journal of Computer and System Sciences, 78 (5): 1404-1422, 2012.
9. Cesa-Bianchi, Nicolo, Lugosi, Gabor, and Stoltz, Gilles. Regret minimization under partial monitoring. Mathematics of Operations Research, 31(3):562-580, 2006.
10. Chen, Wei, Wang, Yajun, and Yuan, Yang. Combinatorial multi-armed bandit: General framework and applications. In Proceedings of the 30th International Conference on Machine Learning (ICML-13), pp. 151-159, 2013.
11. Gai, Yi, Krishnamachari, Bhaskar, and Jain, Rahul. Combinatorial network optimization with unknown variables: Multi-armed bandits with linear rewards and individual observations. IEEE/ACM Trans. Netw., 20(5):1466- 1478, October 2012. ISSN 1063-6692.
12. Kozen, Dexter. The design and analysis of algorithms. Springer, 1992.
13. Lai, Tze Leung and Robbins, Herbert. Asymptotically efficient adaptive allocation rules. Advances in applied mathematics, 6(1):4-22, 1985.
14. Littlestone, Nick and Warmuth, Manfred K. The weighted majority algorithm. In Foundations of Computer Science, 1989., 30th Annual Symposium on, pp. 256-261. IEEE, 1989.
15. Piccolboni, Antonio and Schindelhauer, Christian. Discrete prediction games with arbitrary feedback and loss. In Computational Learning Theory, pp. 208-223. Springer, 2001.
16. Robbins, Herbert. Some aspects of the sequential design of experiments. In Herbert Robbins Selected Papers, pp. 169-177. Springer, 1985.
17. Vovk, Volodimir G. Aggregating strategies. In Proc. Third Workshop on Computational Learning Theory, pp. 371- 383. Morgan Kaufmann, 1990.