A potential-based framework for online multi-class learning with partial feedback

Journal of Machine Learning Research

Volumn 9, Issue , 2010, Pages 900-907

  Wang, Shijun ^a   Jin, Rong ^b   Valizadegan, Hamed ^b  

^a NATIONAL INSTITUTES OF HEALTH   (United States)

^b Michigan State University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CLASS LABELS; DATA SETS; EMPIRICAL STUDIES; EXPONENTIAL GRADIENT ALGORITHMS; GRADIENT DESCENT; HIGH DIMENSIONAL DATA; MISTAKE BOUNDS; MULTI-CLASS; ONLINE LEARNING; PARTIAL FEEDBACK; POTENTIAL FUNCTION; WEIGHT VECTOR;

ALGORITHMS; ARTIFICIAL INTELLIGENCE;

E-LEARNING;

EID: 84862291188     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Conference Paper

References (13)

1. Auer, P., Cesa-Bianchi, N., Freund, Y., & Schapire, R. E. (2003). The nonstochastic multiarmed bandit problem. SIAM J. Comput., 32(1), 48-77.
2. Cesa-Bianchi, N. & Lugosi, G. (2006). Prediction, Learning, and Games. Cambridge University Press.
3. Crammer, K., Singer, Y., & Warmuth, K. (2003). Ultraconservative online algorithms for multiclass problems. JMLR, 3, 2003.
4. Even-Dar, E., Mannor, S., & Mansour, Y. (2002). Pac bounds for multi-armed bandit and markov decision processes. In COLT '02, pages 255-270, London, UK. Springer-Verlag.
5. Even-Dar, E., Mannor, S., & Mansour, Y. (2006). Action elimination and stopping conditions for the multi-armed bandit and reinforcement learning problems. JMLR, 7, 1079-1105.
6. Grove, A. J., Littlestone, N., & Schuurmans, D. (2001). General convergence results for linear discriminant updates. Mach. Learn., 43(3), 173-210.
7. Kakade, S. M., Shalev-Shwartz, S., & Tewari, A. (2008). Efficient bandit algorithms for online multi-class prediction. In ICML '08, pages 440-447, New York, NY, USA. ACM.
8. Kivinen, J. & Warmuth, M. K. (1995). Additive versus exponentiated gradient updates for linear prediction. In STOC '95, pages 209-218, New York, NY, USA. ACM.
9. Langford, J. & Tong, Z. (2007). The epoch-greedy algorithm for contextual multi-armed bandits. In NIPS '07.
10. Lewis, D. D., Yang, Y., Rose, T., & Li, F. (2004). Rcv1: A new benchmark collection for text categorization research. JMLR, 5, 361-397.
11. Littlestone, N. (1988). Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Mach. Learn., 2(4), 285-318.
12. Mannor, S. & Tsitsiklis, J. N. (2004). The sample complexity of exploration in multi-armed bandit problem. JMLR, 5, 623-648.
13. Rosenblatt, F. (1958). The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review, 65, 386-408.