Soft-Bayes: Prod for Mixtures of Experts with Log-Loss

[edit]

Laurent Orseau, Tor Lattimore, Shane Legg ;
Proceedings of the 28th International Conference on Algorithmic Learning Theory, PMLR 76:372-399, 2017.

Abstract

We consider prediction with expert advice under the log-loss with the goal of deriving efficient and robust algorithms. We argue that existing algorithms such as exponentiated gradient, online gradient descent and online Newton step do not adequately satisfy both requirements. Our main contribution is an analysis of the Prod algorithm that is robust to any data sequence and runs in linear time relative to the number of experts in each round. Despite the unbounded nature of the log-loss, we derive a bound that is independent of the largest loss and of the largest gradient, and depends only on the number of experts and the time horizon. Furthermore we give a Bayesian interpretation of Prod and adapt the algorithm to derive a tracking regret.

Related Material