Sequential Probability Assignment with Binary Alphabets and Large Classes of Experts

Abstract

We analyze the problem of sequential probability assignment for binary outcomes with side information and logarithmic loss, where regret—or, redundancy—ismeasured with respect to a (possibly infinite) class of experts. We provide upper and lower bounds for minimax regret in terms of sequential complexities of the class, introduced in [14, 13]. These… (More)

Topics

Cite this paper

@article{Rakhlin2015SequentialPA, title={Sequential Probability Assignment with Binary Alphabets and Large Classes of Experts}, author={Alexander Rakhlin and Karthik Sridharan}, journal={CoRR}, year={2015}, volume={abs/1501.07340} }