Competing with Markov prediction strategies
Machine Learning
2007-05-23 v1
Abstract
Assuming that the loss function is convex in the prediction, we construct a prediction strategy universal for the class of Markov prediction strategies, not necessarily continuous. Allowing randomization, we remove the requirement of convexity.
Cite
@article{arxiv.cs/0607136,
title = {Competing with Markov prediction strategies},
author = {Vladimir Vovk},
journal= {arXiv preprint arXiv:cs/0607136},
year = {2007}
}
Comments
11 pages