Nonasymptotic control of the MLE for misspecified nonparametric hidden Markov models

We study the problem of estimating an unknown time process distribution using nonparametric hidden Markov models in the misspecified setting, that is when the true distribution of the process may not come from a hidden Markov model. We show that when the true distribution is exponentially mixing and satisfies a forgetting assumption, the maximum likelihood estimator recovers the best approximation of the true distribution. We prove a finite sample bound on the resulting error and show that it is optimal in the minimax sense–up to logarithmic factors–when the model is well specified.

[1]  E. Vernet.  Non Parametric Hidden Markov Models with Finite State Space: Posterior Concentration Rates , 2015, 1511.08624.

[2]  Luc Lehéricy.  State-by-state Minimax Adaptive Estimation for Nonparametric Hidden Markov Models , 2018, J. Mach. Learn. Res..

[3]  Gersende Fort,et al.  Forgetting the initial distribution for Hidden Markov Models , 2007 .

[4]  R. Douc,et al.  Asymptotic properties of the maximum likelihood estimation in misspecified Hidden Markov models , 2011, 1110.0356.

[5]  Laurent Mevel,et al.  Asymptotical statistics of misspecified hidden Markov models , 2004, IEEE Transactions on Automatic Control.

[6]  Zacharias Psaradakis,et al.  Maximum Likelihood Estimation in Possibly Misspecified Dynamic Models with Time Inhomogeneous Markov Regimes , 2016, 1612.04932.

[7]  R. Douc,et al.  CONSISTENCY OF THE MAXIMUM LIKELIHOOD ESTIMATOR FOR GENERAL HIDDEN MARKOV MODELS , 2009, 0912.4480.

[8]  Fabrice Lefèvre,et al.  Non-parametric probability estimation for HMM-based automatic speech recognition , 2003, Comput. Speech Lang..

[9]  R. C. Bradley.  Basic properties of strong mixing conditions. A survey and some open questions , 2005, math/0511078.

[10]  Anima Anandkumar,et al.  A Method of Moments for Mixture Models and Hidden Markov Models , 2012, COLT.

[11]  H. Weimerskirch,et al.  Movement models provide insights into variation in the foraging effort of central place foragers , 2014 .

[12]  E. Rio,et al.  Bernstein inequality and moderate deviations under strong mixing conditions , 2012, 1202.4777.

[13]  C. Maugis-Rabusseau,et al.  Adaptive density estimation for clustering with gaussian mixtures , 2013 .

[14]  Dean Alderucci.  A SPECTRAL ALGORITHM FOR LEARNING HIDDEN MARKOV MODELS THAT HAVE SILENT STATES , 2015 .

[15]  P. Doukhan,et al.  Weak Dependence: With Examples and Applications , 2007 .

[16]  R. Douc,et al.  Asymptotic properties of the maximum likelihood estimator in autoregressive models with Markov regime , 2004, math/0503681.

[17]  Martin F. Lambert,et al.  A non-parametric hidden Markov model for climate state identification , 2003 .

[18]  Laurent Mevel,et al.  Exponential Forgetting and Geometric Ergodicity in Hidden Markov Models , 2000, Math. Control. Signals Syst..

[19]  L. Baum,et al.  Statistical Inference for Probabilistic Functions of Finite State Markov Chains , 1966 .

[20]  Laurent Couvreur,et al.  Wavelet-based non-parametric HMM's: theory and applications , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[21]  S. Geman,et al.  Hidden Markov Random Fields , 1995 .

[22]  R. Douc,et al.  Posterior consistency for partially observed Markov models , 2016, Stochastic Processes and their Applications.

[23]  R. Douc,et al.  Asymptotics of the maximum likelihood estimator for general hidden Markov models , 2001 .

[24]  Yohann de Castro,et al.  Minimax Adaptive Estimation of Nonparametric Hidden Markov Models , 2015, J. Mach. Learn. Res..

[25]  Sylvain Arlot,et al.  A survey of cross-validation procedures for model selection , 2009, 0907.4728.

[26]  C. Yau,et al.  Bayesian non‐parametric hidden Markov models with applications in genomics , 2011 .

[27]  B. Leroux.  Maximum-likelihood estimation for hidden Markov models , 1992 .

[28]  A. Barron.  THE STRONG ERGODIC THEOREM FOR DENSITIES: GENERALIZED SHANNON-MCMILLAN-BREIMAN THEOREM' , 1985 .

[29]  Yohann De Castro,et al.  Consistent Estimation of the Filtering and Marginal Smoothing Distributions in Nonparametric Hidden Markov Models , 2015, IEEE Transactions on Information Theory.

[30]  Jean-Marc Robin,et al.  Non‐parametric estimation of finite mixtures from repeated measurements , 2016 .

[31]  H. Holzmann,et al.  Nonparametric identification of hidden Markov models , 2014 .

[32]  P. Massart,et al.  Concentration inequalities and model selection , 2007 .

[33]  A. V. D. Vaart,et al.  Adaptive Bayesian density estimation with location-scale mixtures , 2010 .