Online Learning with Automata-based Expert Sequences
release_nktk6f7krfhync6pmpfqffeqq4
by
Mehryar Mohri, Scott Yang
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) |
1705.00132v3
access all versions, variants, and formats of this works (eg, pre-prints)