Spectral dimensionality reduction for HMMs

Hidden Markov Models (HMMs) can be accurately approximated using co-occurrence frequencies of pairs and triples of observations by using a fast spectral method in contrast to the usual slow methods like EM or Gibbs sampling. We provide a new spectral method which significantly reduces the number of model parameters that need to be estimated, and generates a sample complexity that does not depend on the size of the observation vocabulary. We present an elementary proof giving bounds on the relative accuracy of probability estimates from our model. (Correlaries show our bounds can be weakened to provide either L1 bounds or KL bounds which provide easier direct comparisons to previous work.) Our theorem uses conditions that are checkable from the data, instead of putting conditions on the unobservable Markov transition matrix.

[1]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  W. Hoeffding.  Probability Inequalities for sums of Bounded Random Variables , 1963 .

[3]  Sebastiaan A. Terwijn,et al.  On the Learnability of Hidden Markov Models , 2002, ICGI.

[4]  Herbert Jaeger,et al.  Observable Operator Models for Discrete Stochastic Time Series , 2000, Neural Computation.

[5]  Marcel Paul Schützenberger,et al.  On the Definition of a Family of Automata , 1961, Inf. Control..

[6]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[7]  L. Baum,et al.  A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains , 1970 .

[8]  Byron Boots,et al.  Reduced-Rank Hidden Markov Models , 2009, AISTATS.

[9]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[10]  Byron Boots,et al.  An Online Spectral Learning Algorithm for Partially Observable Nonlinear Dynamical Systems , 2011, AAAI.

[11]  Jack W. Carlyle,et al.  Realizations by Stochastic Finite Automata , 1971, J. Comput. Syst. Sci..

[12]  Le Song,et al.  Hilbert Space Embeddings of Hidden Markov Models , 2010, ICML.

[13]  Sham M. Kakade,et al.  A spectral algorithm for learning Hidden Markov Models , 2008, J. Comput. Syst. Sci..