Online Learning with Automata-based Expert Sequences release_nktk6f7krfhync6pmpfqffeqq4

by Mehryar Mohri, Scott Yang

Released as a article .

2017  

Abstract

We consider a general framework of online learning with expert advice where regret is defined with respect to sequences of experts accepted by a weighted automaton. Our framework covers several problems previously studied, including competing against k-shifting experts. We give a series of algorithms for this problem, including an automata-based algorithm extending weighted-majority and more efficient algorithms based on the notion of failure transitions. We further present efficient algorithms based on an approximation of the competitor automaton, in particular n-gram models obtained by minimizing the ∞-Rényi divergence, and present an extensive study of the approximation properties of such models. Finally, we also extend our algorithms and results to the framework of sleeping experts.
In text/plain format

Archived Files and Locations

application/pdf  944.5 kB
file_5o6sfyxjmbconpe4tccbel32gu
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2017-05-13
Version   v3
Language   en ?
arXiv  1705.00132v3
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 05fea4d4-a150-40e2-b8cf-9e18c1914620
API URL: JSON