Multiclass classification with bandit feedback using adaptive regularization

Machine Learning

Volumn 90, Issue 3, 2013, Pages 347-383

  Crammer, Koby ^a   Gentile, Claudio ^b  

^a TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

^b UNIVERSITY OF INSUBRIA   (Italy)

Author keywords

Online learning; Regret; Upper confidence bound

Indexed keywords

ADAPTIVE REGULARIZATION; BANDIT FEEDBACKS; EXPLORATION AND EXPLOITATION; MULTI-CLASS; MULTI-CLASS CLASSIFICATION; ON-LINE ALGORITHMS; ONLINE LEARNING; PARTIAL FEEDBACK; PERCEPTRON; PROBABILISTIC MODELS; RANDOM SAMPLING; REAL-WORLD; REGRET; SECOND ORDERS; SINGLE-BIT; TEXT CLASSIFICATION; UPPER CONFIDENCE BOUND; VOWEL RECOGNITION;

LEARNING ALGORITHMS;

CLASSIFICATION (OF INFORMATION);

EID: 84874710652     PISSN: 08856125     EISSN: 15730565     Source Type: Journal    
DOI: 10.1007/s10994-012-5321-8     Document Type: Article

References (31)

1. Auer, P. (2003). Using confidence bounds for exploitation-exploration trade-offs. Journal of Machine Learning Research, 3, 397-422.
2. Azoury, K. S., & Warmuth, M. K. (2001). Relative loss bounds for online density estimation with the exponential family of distributions. Machine Learning, 43, 211-246.
3. Blitzer, J., Dredze, M., & Pereira, F. (2007). Biographies, Bollywood, boom-boxes and blenders: domain adaptation for sentiment classification. In Association of computational linguistics (ACL).
4. Cesa-Bianchi, N., Conconi, A., & Gentile, C. (2005). A second-order perceptron algorithm. SIAM Journal on Computing, 43, 640-668.
5. Cesa-Bianchi, N., Gentile, C., & Orabona, F. (2009). Robust bounds for classification via selective sampling. In Proc. 26th ICML.
6. Crammer, K., & Singer, Y. (2002). On the learnability and design of output codes for multiclass problems. Machine Learning, 47, 201-233.
7. Crammer, K., & Singer, Y. (2003). Ultraconservative online algorithms for multiclass problems. Journal of Machine Learning Research, 3, 951-991.
8. Crammer, K., Dredze, M., & Kulesza, A. (2009a). Multi-class confidence weighted algorithms. In EMNLP 2009.
9. Crammer, K., Kulesza, A., & Dredze, M. (2009b). Adaptive regularization of weighted vectors. In Nips 2009.
10. Dani, V., Hayes, T., & Kakade, S. (2008). Stochastic linear optimization under bandit feedback. In Colt 2008.
11. Dekel, O., Gentile, C., & Sridharan, K. (2010). Robust selective sampling from single and multiple teachers. In Colt 2010.
12. Dredze, M., Crammer, K., & Pereira, F. (2008). Confidence-weighted linear classification. In ICML 2008.
13. 1-ball for learning in high dimensions. In ICML 2008 (pp. 272-279).
14. Hazan, E., & Kale, S. (2011). Newtron: an efficient bandit algorithm for online multiclass prediction. In NIPS 2011.
15. Hoerl, A., & Kennard, R. (1970). Ridge regression: biased estimation for nonorthogonal problems. Technometrics, 12, 55-67.
16. Kakade, S., & Tewari, A. (2008). On the generalization ability of online strongly convex programming algorithm. In Nips 2008.
17. Kakade, S., Shalev-Shwartz, S., & Tewari, A. (2008). Efficient bandit algorithms for online multiclass prediction. In ICML 2008.
18. Kilanski, K., Malkin, J., Li, X., Wright, R., & Bilmes, J. (2006). The Vocal Joystick data collection effort and vowel corpus. In Interspeech, Pittsburgh, PA.
19. Langford, J., & Zhang, T. (2007). The epoch-greedy algorithm for contextual multi-armed bandits. In Nips 2007.
20. Lewis, D. D., Yang, Y., Rose, T. G., & Li, F. (2004). Rcv1: a new benchmark collection for text categorization research. Journal of Machine Learning Research, 5, 361-397.
21. Lin, H., Bilmes, J., & Crammer, K. (2009). How to loose confidence: probabilistic linear machines for multiclass classification. In INTERSPEECH (pp. 2559-2562).
22. Liu, J., & Ye, J. (2009). Efficient Euclidean projections in linear time. In ICML 2009 (p. 83).
23. Lu, T., Pal, D., & Pal, M. (2010). Showing relevant ads via Lipschitz context multi-armed bandits. In Aistat 2010.
24. Rigollet, P., & Zeevi, A. (2010). Nonparametric bandits with covariates. In Colt 2010.
25. Rosenblatt, F. (1958). The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 65, 386-407.
26. Sandhaus, E. (2008). The New York Times annotated corpus. Philadelphia: Linguistic Data Consortium.
27. Strehl, A., & Littman, M. (2008). Online linear regression and its application to model-based reinforcement learning. In NIPS 2008.
28. Valizadegan, H., Jin, R., & Wang, S. (2011). Learning to trade off between exploration and exploitation in multiclass bandit prediction. In KDD 2011.
29. Walsh, T. J., Szita, I., Diuk, C., & Littman, M. L. (2009). Exploring compact reinforcement-learning representations with linear regression. In UAI 2008 & Rutgers Univ. Tech. Rep.
30. Wang, C., Kulkarni, S., & Poor, V. (2005). Bandit problems with side observation. IEEE Transactions on Automatic Control, 50, 338-355.
31. Wang, S., Jin, R., & Valizadegan, H. (2010). A potential-based framework for online multi-class learning with partial feedback. In Aistat 2010.