Abstract
In this paper we continue study of the games of prediction with expert advice with uncountably many experts. A convenient interpretation of such games is to construe the pool of experts as one “stochastic predictor”, who chooses one of the experts in the pool at random according to the prior distribution on the experts and then replicates the (deterministic ) predictions of the chosen expert. We notice that if the stochastic predictor's total loss is at most L with probability at least p then the learner's loss can be bounded by cL + aln \(\frac{1}{{\text{P}}}\) for the usual constants c and a. This interpretation is used to revamp known results and obtain new results on tracking the best expert. It is also applied to merging overconfident experts and to fitting polynomials to data.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Auer, P., & Long, P. (1994). Simulating access to hidden information while learning. Proceedings of the 26th Annual ACM Symposium on Theory of Computing (pp. 263–272). New York: Assoc. Comput. Mach.
Carlson, B.C. (1977). Special functions of applied mathematics. New York: Academic Press.
Cesa-Bianchi, N., Freund, Y., Helmbold, D.P., Haussler, D., Schapire, R.E., & Warmuth, M.K. (1993). How to use expert advice. Proceedings of the 25th Annual ACM Symposium on Theory of Computing (pp. 382–391). New York: Assoc. Comput. Mach.
Cesa-Bianchi, N., Freund, Y., Helmbold, D.P., & Warmuth, M.K. (1996). On-line prediction and conversion strategies. Machine Learning, 25, 71–110.
Cesa-Bianchi, N., Helmbold, D.P., & Panizza, S. (1996). On Bayes methods for on-line Boolean prediction. Proceedings of the 9th Annual ACM Conference on Computational Learning Theory (pp. 314–324). New York: Assoc. Comput. Mach.
Cover, T., & Ordentlich, E. (1996). Universal portfolios with side information. IEEE Trans. Inform. Theory, 42, 348–363.
Dawid, A.P. (1986). Probability forecasting. In S. Kotz & N.L. Johnson (Eds.), Encyclopedia of Statistical Sciences (Vol. 7). New York: Wiley.
DeSantis, A., Markowsky, G., & Wegman, M.N. (1988). Learning probabilistic prediction functions. Proceedings of the 29th Annual IEEE Symposium on Foundations of Computer Science (pp. 110–119). Los Alamitos, CA: IEEE Comput. Soc.
Feder, M., Merhav, N., & Gutman, M. (1992). Universal prediction of individual sequences. IEEE Trans. Inform. Theory, 38, 1258–1270.
Freund, Y. (1996). Predicting a binary sequence almost as well as the optimal biased coin. Proceedings of the 9th Annual ACM Conference on Computational Learning Theory (pp. 89–98). New York: Assoc. Comput. Mach.
Freund, Y., Schapire, R., Singer, Y., & Warmuth, M. (1997). Using and combining predictors that specialize. Proceedings of the 29th Annual ACM Symposium on Theory of Computing. New York: Assoc. Comput. Mach.
Haussler, D., Kivinen, J., & Warmuth, M.K. (1994). Tight worst-case loss bounds for predicting with expert advice. (Technical Report UCSC-CRL-94-36). University of California, Santa Cruz, CA, revised December 1994. Short version in P. Vitányi (Ed.), Computational Learning Theory. Lecture Notes in Computer Science (Vol. 904). Berlin: Springer (1995).
Helmbold, D., & Schapire, R. (1997). Predicting nearly as well as the best pruning of a decision tree. Machine Learning, 27, 51–68.
Herbster, M., & Warmuth, M. (1995). Tracking the best expert. Proceedings of the 12th International Conference on Machine Learning (pp. 286–294). Morgan Kaufmann. To appear in Machine Learning.
Herbster, M., & Warmuth, M. (1997). Tracking the best expert, II. Manuscript.
Lauritzen, S.L., & Spiegelhalter, D.J. (1988). Local computations with probabilities on graphical structures and their application to expert systems (with discussion). J. R. Statist. Soc. B, 50, 157–224. Also in (Shafer and Pearl, 1990).
Littlestone, N., & Warmuth, M.K. (1994). The weighted majority algorithm. Inform. Computation, 108, 212–261.
Pearl, J. (1986). Fusion, propagation, and structuring in belief networks. Artificial Intelligence, 29, 241–288. Also in (Shafer and Pearl, 1990).
Rissanen, J. (1983). A universal prior for integers and estimation by minimum description length. Ann. Statist., 11, 416–431.
Shafer, G., & Pearl, J. (Eds.) (1990). Uncertain reasoning. San Mateo, CA: Morgan Kauffman.
Takimoto, E., Maruoka, A., & Vovk, V. (1998). Predicting nearly as well as the best pruning of a decision tree through dynamic programming scheme. Submitted for publication.
Vovk, V. (1990). Aggregating strategies. Proceedings of the 3rd Annual Workshop on Computational Learning Theory (pp. 371–383). San Mateo, CA: Morgan Kaufmann.
Vovk, V. (1992). Universal forecasting algorithms. Inform. Computation, 96, 245–277.
Vovk, V. (1997a). Derandomizing stochastic prediction strategies. Proceedings of the 9th Annual ACM Conference on Computational Learning Theory (pp. 32–44). New York: Assoc. Comput. Mach.
Vovk, V. (1997b). On-line competitive linear regression. M.I. Jordan, M.J. Kearns, & S.A. Solla (Eds.), Advances in Neural Information Processing Systems 10 (pp. 364–370). Cambridge, MA: MIT Press.
Vovk, V. (1998). A game of prediction with expert advice. J. Comput. Inform. Syst., 56, 153–173.
Vovk, V., & Watkins, C.J.H.C. (1998). Universal portfolio selection. Proceedings of the 11th Annual ACM Conference on Computational Learning Theory (pp. 12–23). New York: Assoc. Comput. Mach.
Watkins, C.J.H.C. (1997). How to use advice from small numbers of experts. (Technical Report CSD-TR-97-16) Department of Computer Science, Royal Holloway, University of London.
Yamanishi, K. (1995). Randomized approximate aggregating strategies and their applications to prediction and discrimination. Proceedings of the 8th Annual ACMConference on Computational Learning Theory (pp. 83–90). New York: Assoc. Comput. Mach.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Vovk, V. Derandomizing Stochastic Prediction Strategies. Machine Learning 35, 247–282 (1999). https://doi.org/10.1023/A:1007595032382
Issue Date:
DOI: https://doi.org/10.1023/A:1007595032382