A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting

Journal of Computer and System Sciences - Tập 55 - Trang 119-139 - 1997
Yoav Freund1, Robert E Schapire1
1AT&T Labs, 180 Park Avenue, Florham Park, New Jersey, 07932

Tài liệu tham khảo

Baum, 1989, What size net gives valid generalization?, Adv. Neural Inform. Process. Systems I, 81 Blackwell, 1956, An analog of the minimax theorem for vector payoffs, Pacific J. Math., 6, 1, 10.2140/pjm.1956.6.1 L. Breiman, 1996, Bias, variance, and arcing classifiers, Statistics Dept. University of California N. Cesa-Bianchi, Y. Freund, D. P. Helmhold, D. Haussler, R. E. Schapire, M. K. Warmuth, How to use expert advice, Proceedings of the Twenty-Fifth Annual ACM Symposium on the Theory of Computing, 1993, 382, 391 T. H. Chung, Approximate methods for sequential decision making using expert advice, Proceedings of the Seventh Annual ACM Conference on Computational Learning Theory, 1994, 183, 189 Cover, 1991, Universal portfolios, Math. Finance, 1, 1, 10.1111/j.1467-9965.1991.tb00002.x Dietterich, 1995, Solving multiclass learning problems via error-correcting output codes, J. Artif. Intell. Res., 2, 263, 10.1613/jair.105 Drucker, 1996, Boosting decision trees, Adv. Neural Inform. Process. Systems, 8 Drucker, 1993, Boosting performance in neural networks, Int. J. Pattern Recognition Artif. Intell., 7, 705, 10.1142/S0218001493000352 Y. Freund, 1993, Data Filtering and Distribution Modeling Algorithms for Machine Learning, University of California at Santa Cruz Freund, 1995, Boosting a weak learning algorithm by majority, Inform. and Comput., 121, 256, 10.1006/inco.1995.1136 Y. Freund, R. E. Schapire, Experiments with a new boosting algorithm, Machine Learning: Proceedings of the Thirteenth International Conference, 1996, 148, 156 Y. Freund, R. E. Schapire, Game theory, on-line prediction and boosting, Proceedings of the Ninth Annual Conference on Computational Learning Theory, 1996, 325, 332 Hannan, 1957, Approximation to Bayes risk in repeated play Haussler, 1995, Tight worst-case loss bounds for predicting with expert advice Jackson, 1996, Learning sparse perceptrons, Adv. Neural Inform. Process. Systems, 8 M. Kearns, Y. Mansour, A. Y. Ng, D. Ron, An experimental and theoretical comparison of model selection methods, Proceedings of the Eighth Annual Conference on Computational Learning Theory, 1995 Kearns, 1994 Kivinen, 1994, Using experts for predicting continuous outcomes Littlestone, 1994, The weighted majority algorithm, Inform. and Comput., 108, 212, 10.1006/inco.1994.1009 J. R. Quinlan, Bagging, boosting, and C4.5, Proceedings, Fourteenth National Conference on Artificial Intelligence, 1996 Schapire, 1990, The strength of weak learnability, Machine Learning, 5, 197, 10.1007/BF00116037 Vapnik, 1982 V. G. Vovk, A game of prediction with expert advice, Proceedings of the Eighth Annual Conference on Computational Learning Theory, 1995 V. G. Vovk, Aggregating strategies, Proceedings of the Third Annual Workshop on Computational Learning Theory, 1990, 321, 383 Wenocur, 1981, Some special Vapnik–Chervonenkis classes, Discrete Mathematics, 33, 313, 10.1016/0012-365X(81)90274-0