Online Non-Additive Path Learning under Full and Partial Information
Abstract
We study the problem of online path learning with non-additive gains, which is a central problem appearing in several applications, including ensemble structured prediction. We present new online algorithms for path learning with non-additive count-based gains for the three settings of full information, semi-bandit and full bandit with very favorable regret guarantees. A key component of our algorithms is the definition and computation of an intermediate context-dependent automaton that enables us to use existing algorithms designed for additive gains. We further apply our methods to the important application of ensemble structured prediction. Finally, beyond count-based gains, we give an efficient implementation of the EXP3 algorithm for the full bandit setting with an arbitrary (non-additive) gain.
Cite
@article{arxiv.1804.06518,
title = {Online Non-Additive Path Learning under Full and Partial Information},
author = {Corinna Cortes and Vitaly Kuznetsov and Mehryar Mohri and Holakou Rahmanian and Manfred K. Warmuth},
journal= {arXiv preprint arXiv:1804.06518},
year = {2019}
}