• A lower bound for learning distributions generated by probabilistic automata 

    Balle Pigem, Borja de; Castro Rabal, Jorge; Gavaldà Mestre, Ricard (Springer, 2010)
    Text en actes de congrés
    Accés obert
    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. ...
  • Adaptively learning probabilistic deterministic automata from data streams 

    Balle Pigem, Borja de; Castro Rabal, Jorge; Gavaldà Mestre, Ricard (2014-07)
    Article
    Accés restringit per política de l'editorial
    Markovian models with hidden state are widely-used formalisms for modeling sequential phenomena. Learnability of these models has been well studied when the sample is given in batch mode, and algorithms with PAC-like ...
  • Learning PDFA with asynchronous transitions 

    Balle Pigem, Borja de; Castro Rabal, Jorge; Gavaldà Mestre, Ricard (Springer, 2010)
    Comunicació de congrés
    Accés obert
    In this paper we extend the PAC learning algorithm due to Clark and Thollard for learning distributions generated by PDFA to automata whose transitions may take varying time lengths, governed by exponential distributions.
  • Learning probabilistic automata : a study in state distinguishability 

    Balle Pigem, Borja de; Castro Rabal, Jorge; Gavaldà Mestre, Ricard (2013-02-18)
    Article
    Accés restringit per política de l'editorial
    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 ...
  • Note: More efficient conversion of equivalence-query algorithms to PAC algorithms 

    Gavaldà Mestre, Ricard (2009-05)
    Report de recerca
    Accés obert
    We present a method for transforming an Equivalence-query algorithm using Q queries into a PAC-algorithm using Q/epsilon + O( (Q^(2/3) / epsilon ) * log(Q / delta) examples in expectation. The method is a variation of that ...
  • Query, PACS and simple-PAC learning 

    Castro Rabal, Jorge; Guijarro Guillem, David (1998-01)
    Report de recerca
    Accés obert
    We study a distribution dependent form of PAC learning that uses probability distributions related to Kolmogorov complexity. We relate the PACS model, defined by Denis, D'Halluin and Gilleron, with the standard simple-PAC ...
  • Simple PAC learning of simple decision lists 

    Castro Rabal, Jorge; Balcázar Navarro, José Luis (1995-06)
    Report de recerca
    Accés obert
    We prove that log n-decision lists - the class of decision lists such that all their terms have low Kolmogorov complexity - are learnable in the simple PAC learning model. The proof is based on a transformation from an ...