Learning probabilistic automata : a study in state distinguishability
Rights accessRestricted access - publisher's policy
European Commisision's projectPASCAL2 - Pattern Analysis, Statistical Modelling and Computational Learning 2 (EC-FP7-216886)
Known algorithms for learning PDFA can only be shown to run in time polynomial in the so-called distinguishability μ of the target machine, besides the number of states and the usual accuracy and confidence parameters. We show that the dependence on μ is necessary in the worst case for every algorithm whose structure resembles existing ones. As a technical tool, a new variant of Statistical Queries termed View the MathML source-queries is defined. We show how to simulate View the MathML source-queries using classical Statistical Queries and show that known PAC algorithms for learning PDFA are in fact statistical query algorithms. Our results include a lower bound: every algorithm to learn PDFA with queries using a reasonable tolerance must make Ω(1/μ1−c) queries for every c>0. Finally, an adaptive algorithm that PAC-learns w.r.t. another measure of complexity is described. This yields better efficiency in many cases, while retaining the same inevitable worst-case behavior. Our algorithm requires fewer input parameters than previously existing ones, and has a better sample bound.
CitationB. Balle; Castro, J.; Gavaldà, R. Learning probabilistic automata : a study in state distinguishability. "Theoretical computer science", 18 Febrer 2013, vol. 473, p. 46-60.