By Topic

On prediction of individual sequences relative to a set of experts

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
N. Cesa-Bianchi ; Dipt. di Sci. dell'Inf., Milan Univ., Italy ; G. Lugosi

We investigate sequential randomized prediction of an arbitrary binary sequence. The goal of the predictor is to minimize Hamming loss relative to the loss of the best “expert” in a fixed set of experts. We point out a close connection between the prediction problem and empirical process theory. We show upper and lower bounds on the minimax relative loss in terms of the geometry of the class of experts. As a main example, we determine the exact order of magnitude of the minimax relative loss for the class of Markov experts. Furthermore, in the special case of static experts, we completely characterize the minimax relative loss in terms of the maximal deviation of an associated Rademacher process

Published in:

Information Theory, 1998. Proceedings. 1998 IEEE International Symposium on

Date of Conference:

16-21 Aug 1998