Competing With Strategies
Machine Learning
2013-02-13 v1 Computer Science and Game Theory
Machine Learning
Abstract
We study the problem of online learning with a notion of regret defined with respect to a set of strategies. We develop tools for analyzing the minimax rates and for deriving regret-minimization algorithms in this scenario. While the standard methods for minimizing the usual notion of regret fail, through our analysis we demonstrate existence of regret-minimization methods that compete with such sets of strategies as: autoregressive algorithms, strategies based on statistical models, regularized least squares, and follow the regularized leader strategies. In several cases we also derive efficient learning algorithms.
Cite
@article{arxiv.1302.2672,
title = {Competing With Strategies},
author = {Wei Han and Alexander Rakhlin and Karthik Sridharan},
journal= {arXiv preprint arXiv:1302.2672},
year = {2013}
}