Show simple item record

dc.contributor.authorBalle Pigem, Borja de
dc.contributor.authorCastro Rabal, Jorge
dc.contributor.authorGavaldà Mestre, Ricard
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Llenguatges i Sistemes Informàtics
dc.identifier.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.
dc.description.abstractKnown 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.
dc.format.extent15 p.
dc.subjectÀrees temàtiques de la UPC::Informàtica::Sistemes d'informació
dc.subject.lcshDistributed learning
dc.subject.lcshPAC learning
dc.subject.lcshProbabilistic automata
dc.subject.lcshStatistical queries
dc.titleLearning probabilistic automata : a study in state distinguishability
dc.subject.lemacSistemes distribuits
dc.contributor.groupUniversitat Politècnica de Catalunya. LARCA - Laboratori d'Algorísmia Relacional, Complexitat i Aprenentatge
dc.description.peerreviewedPeer Reviewed
dc.rights.accessRestricted access - publisher's policy
dc.description.versionPostprint (published version)
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/FP7/216886/EU/Pattern Analysis, Statistical Modelling and Computational Learning 2/PASCAL2
local.citation.authorB. Balle; Castro, J.; Gavaldà, R.
local.citation.publicationNameTheoretical computer science

Files in this item


This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder