On learning parametric-output HMMs

30th International Conference on Machine Learning, ICML 2013

Volumn , Issue PART 3, 2013, Pages 1739-1747

  Kontorovich, Aryeh ^a   Nadler, Boaz ^b   Weiss, Roi ^a  

^a BEN GURION UNIVERSITY OF THE NEGEV   (Israel)

^b WEIZMANN INSTITUTE OF SCIENCE   (Israel)

Author keywords

[No Author keywords available]

Indexed keywords

ESTIMATION; LEARNING SYSTEMS; MIXTURES;

LEARNING TASKS; MIXTURE MODEL; OUTPUT PARAMETERS; PARAMETRIC FAMILY; QUADRATIC PROGRAMS; SMALL PERTURBATIONS; STATIONARY DISTRIBUTION; TRANSITION PROBABILITIES;

PARAMETER ESTIMATION;

EID: 84897543977     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (29)

1. Abe, N. and Warmuth, M.K. On the computational complexity of approximating distributions by probabilistic automata. Machine Learning, 9:205-260, 1992.
2. Anandkumar, A., Hsu, D., and Kakade, S.M. A method of moments for mixture models and hidden markov models. In COLT, 2012.
3. Bailly, Raphael. Quadratic weighted automata: Spectral algorithm and likelihood maximization. Journal of Machine Learning Research, 20:147-162, 2011.
4. Balle, Borja, Quattoni, Ariadna, and Carreras, Xavier. Local loss optimization in operator models: A new insight into spectral learning. arXiv preprint arXiv:1206.6393, 2012.
5. Baum, L.E., Petrie, T., Soules, G., and Weiss, N. A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains. Ann. Math. Stat., 41(1):pp. 164-171, 1970.
6. Belkin, M. and Sinha, K. Polynomial learning of distribution families. In Foundations of Computer Science (FOCS), pp. 103-112, 2010.
7. Bickel, P.J., Ritov, Y., and Rydén, T. Asymptotic normality of the maximum-likelihood estimator for general hidden Markov models. Ann. Statist., 26(4):1614-1635, 1998.
8. Cappé, O., Moulines, E., and Rydén, T. Inference in hidden Markov models. Springer Series in Statistics. Springer, New York, 2005.
9. Chang, J.T. Full reconstruction of Markov models on evolutionary trees: identifiability and consistency. Math. Biosci., 137(1):51-73, 1996. (Pubitemid 26307662)
10. Cybenko, G. and Crespi, V. Learning hidden Markov models using nonnegative matrix factorization. IEEE Trans. Information Theory, 57(6):3963-3970, 2011.
11. Daniel, J.W. Stability of the solution of definite quadratic programs. Mathematical Programming, 5:41-53, 1973.
12. Dantzig, G.B., Folkman, J., and Shapiro, N. On the continuity of the minimum sets of a continuous function. J. Math. Anal. Appl., 17:519-548, 1967.
13. den Hertog, D. Interior point approach to linear, quadratic and convex programming, volume 277 of Mathematics and its Applications. Kluwer, Dordrecht, 1994.
14. Douc, R. and Matias, C. Asymptotics of the maximum likelihood estimator for general hidden Markov models. Bernoulli, 7(3):pp. 381-420, 2001. (Pubitemid 33793047)
15. Faragó, A. and Lugosi, G. An algorithm to find the global optimum of left-to-right hidden Markov model parameters. Problems Control Inform. Theory/Problemy Upravlen. Teor. Inform., 18(6):435-444, 1989. (Pubitemid 20645127)
16. Hsu, D., Kakade, S.M., and Zhang, T. A spectral algorithm for learning hidden markov models. In COLT, 2009.
17. Kontorovich, A. and Weiss, R. Uniform Chernoff and Dvoretzky-Kiefer- Wolfowitz-type inequalities for Markov chains and related processes, arxiv:1207.4678. 2012.
18. Kontorovich, Aryeh, Nadler, Boaz, and Weiss, Roi. On learning parametric-output hmms, arxiv:1302.6009. 2013.
19. Lakshminarayanan, B. and Raich, R. Non-negative matrix factorization for parameter estimation in hidden markov models. In Machine Learning for Signal Processing (MLSP), pp. 89-94, 2010.
20. Lyngsø, R. B. and Pedersen, C. N. Complexity of comparing hidden markov models. In Proceedings of the 12th International Symposium on Algorithms and Computation, pp. 416-428. Springer-Verlag, 2001.
21. Mohri, M. and Rostamizadeh, A. Stability bounds for stationary φ-mixing and β-mixing processes. The Journal of Machine Learning Research, 11:789-814, 2010.
22. Moitra, Ankur and Valiant, Gregory. Settling the polynomial learnability of mixtures of gaussians. In 2010 IEEE 51st Annual Symposium on Foundations of Computer Science, pp. 93-102. IEEE, 2010.
23. Mossel, E. and Roch, S. Learning nonsingular phylogenies and hidden Markov models. Ann. Appl. Probab., 16(2):-583-614, 2006.
24. Nesterov, Y. and Nemirovskii, A. Interior-point polynomial algorithms in convex programming. SIAM, Philadelphia, PA, 1994.
25. Rabiner, L. R. Readings in speech recognition. chapter A tutorial on hidden Markov models and selected applications in speech recognition, pp. 267-296. Morgan Kaufmann, 1990.
26. Roweis, S. and Ghahramani, Z. A unifying review of linear gaussian models. Neural Comput., 11:305-345, February 1999. ISSN 0899-7667.
27. Siddiqi, S. M., Boots, B., and Gordon, G. J. Reduced-rank Hidden Markov Models. In AISTAT, 2010.
28. Song, Le, Boots, Byron, Siddiqi, Sajid, Gordon, Geoffrey, and Smola, Alex. Hilbert space embeddings of hidden markov models. 2010.
29. Terwijn, S. On the learnability of Hidden Markov Models. In Proceedings of the 6th International Colloquium on Grammatical Inference: Algorithms and Applications, ICGI '02, pp. 261-268, London, UK, 2002. Springer-Verlag.