Generalization Bounds for Weighted Automata
Machine Learning
2016-10-26 v1 Formal Languages and Automata Theory
Abstract
This paper studies the problem of learning weighted automata from a finite labeled training sample. We consider several general families of weighted automata defined in terms of three different measures: the norm of an automaton's weights, the norm of the function computed by an automaton, or the norm of the corresponding Hankel matrix. We present new data-dependent generalization guarantees for learning weighted automata expressed in terms of the Rademacher complexity of these families. We further present upper bounds on these Rademacher complexities, which reveal key new data-dependent terms related to the complexity of learning weighted automata.
Keywords
Cite
@article{arxiv.1610.07883,
title = {Generalization Bounds for Weighted Automata},
author = {Borja Balle and Mehryar Mohri},
journal= {arXiv preprint arXiv:1610.07883},
year = {2016}
}