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 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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Abe, N., Warmuth, M.K.: On the computational complexity of approximating distributions by probabilistic automata. Mach. Learn. 9(2-3), 205–260 (1992)
Ben-David, S., Lindenbaum, M.: Learning distributions by their density levels: A paradigm for learning without a teacher. J. Comput. Syst. Sci. 55(1), 171–182 (1997)
Carrasco, R.C., Oncina, J.: Learning deterministic regular grammars from stochastic samples in polynomial time. RAIRO (Theoretical Informatics and Applications) 33(1), 1–20 (1999)
Castro, J., Gavaldà, R.: Towards feasible PAC-learning of probabilistic deterministic finite automata. In: Clark, A., Coste, F., Miclet, L. (eds.) ICGI 2008. LNCS (LNAI), vol. 5278, pp. 163–174. Springer, Heidelberg (2008)
Cesa-Bianchi, N., Lugosi, G.: Prediction, Learning, and Games. Cambridge University Press, New York (2006)
Clark, A., Thollard, F.: PAC-learnability of probabilistic deterministic finite state automata. Journal of Machine Learning Research (2004)
Denis, F., Esposito, Y., Habrard, A.: Learning rational stochastic languages. In: Lugosi, G., Simon, H.U. (eds.) COLT 2006. LNCS (LNAI), vol. 4005, pp. 274–288. Springer, Heidelberg (2006)
Dupont, P., Denis, F., Esposito, Y.: Links between probabilistic automata and hidden markov models: probability distributions, learning models and induction algorithms. Pattern Recognition 38(9), 1349–1371 (2005)
Gavaldà, R., Keller, P.W., Pineau, J., Precup, D.: PAC-learning of markov models with hidden state. In: Fürnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 150–161. Springer, Heidelberg (2006)
Guttman, O., Vishwanathan, S.V.N., Williamson, R.C.: Learnability of probabilistic automata via oracles. In: Jain, S., Simon, H.U., Tomita, E. (eds.) ALT 2005. LNCS (LNAI), vol. 3734, pp. 171–182. Springer, Heidelberg (2005)
Hsu, D., Kakade, S.M., Zhang, T.: A spectral algorithm for learning hidden markov models. CoRR abs/0811.4413 (2008)
Kearns, M.: Efficient noise-tolerant learning from statistical queries. J. ACM 45(6), 983–1006 (1998)
Kearns, M.J., Mansour, Y., Ron, D., Rubinfeld, R., Schapire, R.E., Sellie, L.: On the learnability of discrete distributions. In: STOC, pp. 273–282 (1994)
Lyngsø, R.B., Pedersen, C.N.S.: The consensus string problem and the complexity of comparing hidden markov models. J. Comput. Syst. Sci. 65(3), 545–569 (2002)
Palmer, N., Goldberg, P.W.: PAC-learnability of probabilistic deterministic finite state automata in terms of variation distance. Theor. Comput. Sci. 387(1), 18–31 (2007)
Ron, D., Singer, Y., Tishby, N.: On the learnability and usage of acyclic probabilistic finite automata. J. Comput. Syst. Sci. 56(2), 133–152 (1998)
Vidal, E., Thollard, F., de la Higuera, C., Casacuberta, F., Carrasco, R.C.: Probabilistic finite-state machines - part I. IEEE Trans. Pattern Anal. Mach. Intell. 27(7), 1013–1025 (2005)
Vidal, E., Thollard, F., de la Higuera, C., Casacuberta, F., Carrasco, R.C.: Probabilistic finite-state machines - part II. IEEE Trans. Pattern Anal. Mach. Intell. 27(7), 1026–1039 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Balle, B., Castro, J., Gavaldà, R. (2010). A Lower Bound for Learning Distributions Generated by Probabilistic Automata. In: Hutter, M., Stephan, F., Vovk, V., Zeugmann, T. (eds) Algorithmic Learning Theory. ALT 2010. Lecture Notes in Computer Science(), vol 6331. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-16108-7_17
Download citation
DOI: https://doi.org/10.1007/978-3-642-16108-7_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-16107-0
Online ISBN: 978-3-642-16108-7
eBook Packages: Computer ScienceComputer Science (R0)