Journal
JOURNAL OF COMPUTER AND SYSTEM SCIENCES
Volume 74, Issue 8, Pages 1228-1244Publisher
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.jcss.2007.08.003
Keywords
On-line learning; Predicting individual sequences; Prediction with expert advice; General loss functions
Ask authors/readers for more resources
This paper resolves the problem of predicting as well as the best expert up to an additive term of the order o(n), where n is the length of a sequence of letters from a finite alphabet. We call the games that permit this weakly mixable and give a geometrical characterisation of the class of weakly mixable games. Weak mixability turns out to be equivalent to convexity of the finite part of the set of superpredictions. For bounded games we introduce the Weak Aggregating Algorithm that allows us to obtain additive terms of the form C root n. (C) 2007 Elsevier Inc. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available