Abstract
Weighted automata (WFAs) provide a general framework for the representation of functions mapping strings to real numbers. They include as special instances deterministic finite automata (DFAs), hidden Markov models (HMMs), and predictive states representations (PSRs). In recent years, there has been a renewed interest in weighted automata in machine learning due to the development of efficient and provably correct spectral algorithms for learning weighted automata. Despite the effectiveness reported for spectral techniques in real-world problems, almost all existing statistical guarantees for spectral learning of weighted automata rely on a strong realizability assumption. In this paper, we initiate a systematic study of the learning guarantees for broad classes of weighted automata in an agnostic setting. Our results include bounds on the Rademacher complexity of three general classes of weighted automata, each described in terms of different natural quantities. Interestingly, these bounds underline the key role of different data-dependent parameters in the convergence rates.
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. Machine Learning (1992)
Albert, J., Kari, J.: Digital image compression. In: Handbook of weighted automata. Springer (2009)
Baier, C., GrĂ¶ĂŸer, M., Ciesinski, F.: Model checking linear-time properties of probabilistic systems. In: Handbook of Weighted automata. Springer (2009)
Bailly, R., Denis, F., Ralaivola, L.: Grammatical inference as a principal component analysis problem. In: ICML (2009)
Bailly, R., Denis, F.: Absolute convergence of rational series is semi-decidable. Inf. Comput. (2011)
Balle, B., Carreras, X., Luque, F., Quattoni, A.: Spectral learning of weighted automata: A forward-backward perspective. Machine Learning (2014)
Balle, B., Hamilton, W., Pineau, J.: Methods of moments for learning stochastic languages: unified presentation and empirical comparison. In: ICML (2014)
Balle, B., Mohri, M.: Spectral learning of general weighted automata via constrained matrix completion. In: NIPS (2012)
Balle, B., Mohri, M.: Learning weighted automata. In: CAI (2015)
Balle, B., Panangaden, P., Precup, D.: A canonical form for weighted automata and applications to approximate minimization. In: Logic in Computer Science (LICS) (2015)
Bartlett, P.L., Mendelson, S.: Rademacher and gaussian complexities: risk bounds and structural results. In: Helmbold, D.P., Williamson, B. (eds.) COLT 2001 and EuroCOLT 2001. LNCS (LNAI), vol. 2111, pp. 224–240. Springer, Heidelberg (2001)
Berstel, J., Reutenauer, C.: Noncommutative rational series with applications. Cambridge University Press (2011)
Boots, B., Siddiqi, S., Gordon, G.: Closing the learning-planning loop with predictive state representations. In: RSS (2009)
Carlyle, J.W., Paz, A.: Realizations by stochastic finite automata. J. Comput. Syst. Sci. 5(1) (1971)
Cortes, C., Mohri, M., Rastogi, A.: Lp distance and equivalence of probabilistic automata. International Journal of Foundations of Computer Science (2007)
Devroye, L., Lugosi, G.: Combinatorial methods in density estimation. Springer (2001)
Eilenberg, S.: Automata, Languages and Machines, vol. A. Academic Press (1974)
Fliess, M.: Matrices de Hankel. Journal de Mathématiques Pures et Appliquées 53 (1974)
de Gispert, A., Iglesias, G., Blackwood, G., Banga, E., Byrne, W.: Hierarchical phrase-based translation with weighted finite-state transducers and shallow-n grammars. Computational Linguistics (2010)
Hamilton, W.L., Fard, M.M., Pineau, J.: Modelling sparse dynamical systems with compressed predictive state representations. In: ICML (2013)
Hsu, D., Kakade, S.M., Zhang, T.: A spectral algorithm for learning hidden Markov models. In: COLT (2009)
Ishigami, Y., Tani, S.: Vc-dimensions of finite automata and commutative finite automata with k letters and n states. Discrete Applied Mathematics (1997)
Knight, K., May, J.: Applications of weighted automata in natural language processing. In: Handbook of Weighted Automata. Springer (2009)
Koltchinskii, V., Panchenko, D.: Rademacher processes and bounding the risk of function learning. In: High Dimensional Probability II, pp. 443–459. Birkhäuser (2000)
Kuich, W., Salomaa, A.: Semirings, automata, languages. In: EATCS. Monographs on Theoretical Computer Science, vol. 5. Springer-Verlag, Berlin-New York (1986)
Kulesza, A., Jiang, N., Singh, S.: Low-rank spectral learning with weighted loss functions. In: AISTATS (2015)
Kulesza, A., Rao, N.R., Singh, S.: Low-rank spectral learning. In: AISTATS (2014)
Massart, P.: Some applications of concentration inequalities to statistics. In: Annales de la Faculté des Sciences de Toulouse (2000)
Mirsky, L.: A trace inequality of John von Neumann. Monatshefte fĂ¼r Mathematik (1975)
Mohri, M.: Weighted automata algorithms. In: Handbook of Weighted Automata. Monographs in Theoretical Computer Science, pp. 213–254. Springer (2009)
Mohri, M., Pereira, F.C.N., Riley, M.: Speech recognition with weighted finite-state transducers. In: Handbook on Speech Processing and Speech Comm. Springer (2008)
Mohri, M., Rostamizadeh, A., Talwalkar, A.: Foundations of machine learning. MIT press (2012)
Salomaa, A., Soittola, M.: Automata-Theoretic Aspects of Formal Power Series. Springer-Verlag, New York (1978)
Tropp, J.A.: An Introduction to Matrix Concentration Inequalities (2015). ArXiv abs/1501.01571
Vershynin, R.: Lectures in Geometrical Functional Analysis. Preprint (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Balle, B., Mohri, M. (2015). On the Rademacher Complexity of Weighted Automata. In: Chaudhuri, K., GENTILE, C., Zilles, S. (eds) Algorithmic Learning Theory. ALT 2015. Lecture Notes in Computer Science(), vol 9355. Springer, Cham. https://doi.org/10.1007/978-3-319-24486-0_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-24486-0_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24485-3
Online ISBN: 978-3-319-24486-0
eBook Packages: Computer ScienceComputer Science (R0)