Machine Learning

, Volume 35, Issue 3, pp 247–282

Derandomizing Stochastic Prediction Strategies

Authors

  • V. Vovk
    • Department of Computer Science, Royal HollowayUniversity of London
Article

DOI: 10.1023/A:1007595032382

Cite this article as:
Vovk, V. Machine Learning (1999) 35: 247. doi:10.1023/A:1007595032382

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.

on-line learningprediction with expert advicetracking the best expertregression
Download to read the full article text

Copyright information

© Kluwer Academic Publishers 1999