How to better use expert advice

Machine Learning

Volumn 55, Issue 3, 2004, Pages 271-309

  Yaroshinsky, Rani ^a   El Yaniv, Ran ^a   Seiden, Steven S ^b  

^a TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

^b Louisiana State University   (United States)

Author keywords

Learning from expert advice; Online learning; Online prediction

Indexed keywords

ENTROPY LOSSES; LEARNING FROM EXPERT ADVICE; ONLINE LEARNING; ONLINE PREDICTION;

ALGORITHMS; FUNCTION EVALUATION; GAME THEORY; NUMBER THEORY; ONLINE SYSTEMS; THEOREM PROVING;

LEARNING SYSTEMS;

EID: 3543088062     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1023/B:MACH.0000027784.72823.e4     Document Type: Article

References (21)

1. Auer, P., Cesa-Bianchi, N., & Gentile. C. (2002). Adaptive and self-confident on-line learning algorithms. Journal of Computer and System Sciences, 64:1, 48-75.
2. Blaekwell, D. (1956). An analog of the minimax theorem for vector payoffs. Pacific J. Math., 6, 1-8.
3. Blum, A. (1996). On-line algorithms in machine learning. Dagstuhl workshop on On-Line algorithms.
4. Blum, A. (1997). Empirical support for winnow and weighted-majority algorithms: Results on a calendar scheduling domain. Machine Learning, 26, 5-23.
5. Slum, A., & Burch, C. (1997). On-line learning and the metrical task system problem. In Proceedings of the 10th Annual Conference on Computational Learning Theory (pp. 45-53).
6. Blum, A., Burch, C., & Kalai, A. (1989). Finely-competitive paging. FOCS.
7. Borodin, A., & El-Yaniv, R. (1998). Online Computation and Competitive Analysis. Cambridge University Press.
8. Cesa-Bianchi, N., Freund, Y., Haussler, D., Helmbold, D., Schapire, R., & Warmuth, M. (1997). How to use expert advice. Journal of the ACM, 44:3, 427-485.
9. Chernoff, H. (1954), Rational selection of decision functions. Econometrics, 22, 422-443.
10. Cover, T. (1991.). Universal portfolios. Mathematical Finance, 1:1, 1-29.
11. DeSantis, A., Markowsky, O., & Wegman, M. (1988). Learning probabilistic prediction functions. In FOCS (pp. 110-119).
12. Feder, M., Merhav, N., & Gutman, M. (1902). Universal prediction of individual sequences. IEEE Transactions on Information Theory, 38, 1258-1270.
13. Freund., Y., & Schapire R. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55:1, 119-139.
14. Gentile, C., & Littlestone, N. (1999). The robustness of the p-norm algorithms (pp. 1-11).
15. Haussler, D., Kivinen, J., & Warmuth, M. (1998). Sequential prediction of individual sequences under general loss functions. IEEE Transactions on Information Theory, 44:5, 1906-1925.
16. Helmbold, D., Long, D., & Sherrod, B. (1996). A dynamic disk spin-down technique for mobile computing. In Proceedings of the Second Annual ACM International Conference on Mobile Computing and Networking. ACM/IEEE.
17. Helmbold, D., & Schapire, R. (1995). Predicting nearly as well as the best pruning of a decision tree. In COLT.
18. Littlestone, N., & Warmuth, M. (1994). The weighted majority algorithm. Information and Computation, 108:2, 212-261.
19. Milnor, J. (1954). Games against nature. In R. Thrall, C. Coombs, & R. Davis (Eds.), Decision Processes (pp. 49-60). New York and London: Wiley and Chapman & Hall.
20. Sleator, D., & Tarjan, R. (1985). Amortized efficiency of list update and paging rules. 28:2, 202-208.
21. Vovk, V. (1990). Aggregating strategies. In Proceedings of the Third nnual Workshop on Computational Learning Theory (pp. 371-383).