Thompson Sampling for Online Learning with Linear Experts
Machine Learning
2013-11-05 v1 Machine Learning
Abstract
In this note, we present a version of the Thompson sampling algorithm for the problem of online linear generalization with full information (i.e., the experts setting), studied by Kalai and Vempala, 2005. The algorithm uses a Gaussian prior and time-varying Gaussian likelihoods, and we show that it essentially reduces to Kalai and Vempala's Follow-the-Perturbed-Leader strategy, with exponentially distributed noise replaced by Gaussian noise. This implies sqrt(T) regret bounds for Thompson sampling (with time-varying likelihood) for online learning with full information.
Keywords
Cite
@article{arxiv.1311.0468,
title = {Thompson Sampling for Online Learning with Linear Experts},
author = {Aditya Gopalan},
journal= {arXiv preprint arXiv:1311.0468},
year = {2013}
}