Mostra el registre d'ítem simple

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.date.accessioned2010-12-13T13:06:42Z
dc.date.available2010-12-13T13:06:42Z
dc.date.created2010
dc.date.issued2010
dc.identifier.citationB. Balle; Castro, J.; Gavaldà, R. A lower bound for learning distributions generated by probabilistic automata. A: International Conference on Algorithmic Learning Theory. "21st International Conference on Algorithmic Learning Theory". Canberra: Springer, 2010, p. 179-193.
dc.identifier.isbn978-3-642-16107-0
dc.identifier.urihttp://hdl.handle.net/2117/10556
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 for every algorithm whose structure resembles existing ones. As a technical tool, a new variant of Statistical Queries termed L ∞-queries is defined. We show how these queries can be simulated from samples and observe that known PAC algorithms for learning PDFA can be rewritten to access its target using L∞-queries and standard Statistical Queries. Finally, we show a lower bound: every algorithm to learn PDFA using queries with a resonable tolerance needs a number of queries larger than (1=μ )c for every c < 1.
dc.format.extent15 p.
dc.language.isoeng
dc.publisherSpringer
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
dc.subject.lcshProbably approximately correct learning
dc.subject.lcshPAC learning
dc.subject.lcshPDFA
dc.subject.lcshMachine learning
dc.titleA lower bound for learning distributions generated by probabilistic automata
dc.typeConference report
dc.subject.lemacAprenentatge automàtic
dc.contributor.groupUniversitat Politècnica de Catalunya. LARCA - Laboratori d'Algorísmia Relacional, Complexitat i Aprenentatge
dc.identifier.doi10.1007/978-3-642-16108-7_17
dc.description.peerreviewedPeer Reviewed
dc.rights.accessOpen Access
drac.iddocument2869085
dc.description.versionPostprint (author’s final draft)
upcommons.citation.authorB. Balle; Castro, J.; Gavaldà, R.
upcommons.citation.contributorInternational Conference on Algorithmic Learning Theory
upcommons.citation.pubplaceCanberra
upcommons.citation.publishedtrue
upcommons.citation.publicationName21st International Conference on Algorithmic Learning Theory
upcommons.citation.startingPage179
upcommons.citation.endingPage193


Fitxers d'aquest items

Thumbnail

Aquest ítem apareix a les col·leccions següents

Mostra el registre d'ítem simple

Llevat que s'hi indiqui el contrari, els continguts d'aquesta obra estan subjectes a la llicència de Creative Commons: Reconeixement-NoComercial-SenseObraDerivada 3.0 Espanya