A spectral algorithm for learning hidden Markov models

DOI10.1016/j.jcss.2011.12.025zbMath1244.68065OpenAlexW1825640910WikidataQ56267449 ScholiaQ56267449MaRDI QIDQ439990

Sham M. Kakade, Daniel Hsu, Tong Zhang

Publication date: 17 August 2012

Published in: Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jcss.2011.12.025

zbMATH Keywords

time seriessingular value decompositionhidden Markov modelsunsupervised learningspectral algorithmlatent variable modelslearning probability distributionsobservable operator models

Mathematics Subject Classification ID

Analysis of algorithms (68W40) Learning and adaptive systems in artificial intelligence (68T05)

Related Items

A new method of moments for latent variable models, Inference in finite state space non parametric hidden Markov models and applications, On the optimization landscape of tensor decompositions, Nonparametric estimation of non-exchangeable latent-variable models, Learning Weighted Automata, Quantum-inspired canonical correlation analysis for exponentially large dimensional data, Learning Markov Models Via Low-Rank Optimization, Singular value automata and approximate minimization, Recognizable series on graphs and hypergraphs, A Friendly Tutorial on Mean-Field Spin Glass Techniques for Non-Physicists, Compressed spectral screening for large-scale differential correlation analysis with application in selecting glioblastoma gene modules, Consistent order estimation for nonparametric hidden Markov models, Recovering Structured Probability Matrices, Regime switching model estimation: spectral clustering hidden Markov model, Sequence Classification Using Third-Order Moments, Efficient and effective learning of HMMs based on identification of hidden states, State-by-state Minimax Adaptive Estimation for Nonparametric Hidden Markov Models, The kernel Kalman rule. Efficient nonparametric inference by recursive least-squares and subspace projections, Bisimulation metrics and norms for real-weighted automata, Approximate minimization of weighted tree automata, Hidden Markov models: inverse filtering, belief estimation and privacy protection, Tensor Decompositions for Learning Latent Variable Models (A Survey for ALT), On the Rademacher Complexity of Weighted Automata, Statistical and Computational Guarantees for the Baum-Welch Algorithm, Nonasymptotic control of the MLE for misspecified nonparametric hidden Markov models, Tensor train spectral method for learning of hidden Markov models (HMM), Consistency of the maximum likelihood estimator in seasonal hidden Markov models, Uniform Chernoff and Dvoretzky-Kiefer-Wolfowitz-type inequalities for Markov chains and related processes, General Value Function Networks, A spectral algorithm for latent Dirichlet allocation

Cites Work

• A spectral algorithm for learning mixture models
• Matrices de Hankel
• Realizations by stochastic finite automata
• Linear optimal prediction and innovations representations of hidden Markov models.
• On the learnability of discrete distributions
• On the definition of a family of automata
• Learning Hidden Markov Models Using Nonnegative Matrix Factorization
• An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology
• A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains
• Learning nonsingular phylogenies and hidden Markov models
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item