Mostra el registre d'ítem simple
Learning probabilistic automata : a study in state distinguishability
dc.contributor.author | Balle Pigem, Borja de |
dc.contributor.author | Castro Rabal, Jorge |
dc.contributor.author | Gavaldà Mestre, Ricard |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Llenguatges i Sistemes Informàtics |
dc.date.accessioned | 2013-03-13T13:49:57Z |
dc.date.created | 2013-02-18 |
dc.date.issued | 2013-02-18 |
dc.identifier.citation | B. 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.identifier.issn | 0304-3975 |
dc.identifier.uri | http://hdl.handle.net/2117/18260 |
dc.description.abstract | 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. |
dc.format.extent | 15 p. |
dc.language.iso | eng |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Sistemes d'informació |
dc.subject.lcsh | Distributed learning |
dc.subject.lcsh | PAC learning |
dc.subject.lcsh | Probabilistic automata |
dc.subject.lcsh | Statistical queries |
dc.title | Learning probabilistic automata : a study in state distinguishability |
dc.type | Article |
dc.subject.lemac | Sistemes distribuits |
dc.contributor.group | Universitat Politècnica de Catalunya. LARCA - Laboratori d'Algorísmia Relacional, Complexitat i Aprenentatge |
dc.identifier.doi | 10.1016/j.tcs.2012.10.009 |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | http://www.sciencedirect.com/science/article/pii/S0304397512009309 |
dc.rights.access | Restricted access - publisher's policy |
local.identifier.drac | 11685432 |
dc.description.version | Postprint (published version) |
dc.relation.projectid | info:eu-repo/grantAgreement/EC/FP7/216886/EU/Pattern Analysis, Statistical Modelling and Computational Learning 2/PASCAL2 |
dc.date.lift | 10000-01-01 |
local.citation.author | B. Balle; Castro, J.; Gavaldà, R. |
local.citation.publicationName | Theoretical computer science |
local.citation.volume | 473 |
local.citation.startingPage | 46 |
local.citation.endingPage | 60 |
Fitxers d'aquest items
Aquest ítem apareix a les col·leccions següents
-
Articles de revista [134]
-
Articles de revista [1.046]