A spectral algorithm for learning hidden Markov models

DOI10.1016/J.JCSS.2011.12.025zbMATH Open1244.68065DBLPjournals/jcss/HsuKZ12OpenAlexW1825640910WikidataQ56267449 ScholiaQ56267449MaRDI QIDQ439990FDOQ439990

Authors: Daniel Hsu, Sham M. Kakade, 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

Recommendations

• Tensor train spectral method for learning of hidden Markov models (HMM)
• scientific article; zbMATH DE number 6781356
• scientific article; zbMATH DE number 2019610
• Factorial hidden Markov models
• Learning hidden Markov models from aggregate observations

zbMATH Keywords

latent variable modelstime seriessingular value decompositionunsupervised learninghidden Markov modelsspectral algorithmlearning probability distributionsobservable operator models

Mathematics Subject Classification ID

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

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains
• Title not available (Why is that?)
• On the learnability of discrete distributions
• Title not available (Why is that?)
• Matrices de Hankel
• On the definition of a family of automata
• Title not available (Why is that?)
• Subspace methods for system identification.
• An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology
• Realizations by stochastic finite automata
• Linear optimal prediction and innovations representations of hidden Markov models.
• A probabilistic analysis of EM for mixtures of separated, spherical Gaussians
• Title not available (Why is that?)
• Learning Hidden Markov Models Using Nonnegative Matrix Factorization
• A spectral algorithm for learning mixture models

Cited In (48)

• Compressed spectral screening for large-scale differential correlation analysis with application in selecting glioblastoma gene modules
• Tensor train spectral method for learning of hidden Markov models (HMM)
• Consistency of the maximum likelihood estimator in seasonal hidden Markov models
• Efficient and effective learning of HMMs based on identification of hidden states
• A discrete regularization method for hidden Markov models embedded into reproducing kernel Hilbert space
• Sequence classification via large margin hidden Markov models
• Consistent order estimation for nonparametric hidden Markov models
• Algorithmic polarization for hidden Markov models
• Dimension-free concentration bounds on Hankel matrices for spectral learning
• A New Method for Learning Imprecise Hidden Markov Models
• On the optimization landscape of tensor decompositions
• The kernel Kalman rule. Efficient nonparametric inference by recursive least-squares and subspace projections
• Asymmetric hidden Markov models
• Learning Markov models via low-rank optimization
• A new method of moments for latent variable models
• Spectral methods for learning discrete latent tree models
• Quantum-inspired canonical correlation analysis for exponentially large dimensional data
• Title not available (Why is that?)
• Singular value automata and approximate minimization
• Title not available (Why is that?)
• On equivalent parameter learning in simplified feature space based on Bayesian asymptotic analysis
• A spectral algorithm for latent Dirichlet allocation
• Norm-observable operator models
• General value function networks
• Learning weighted automata
• Regime switching model estimation: spectral clustering hidden Markov model
• Clustering hidden Markov models with variational HEM
• Tensor Decompositions for Learning Latent Variable Models (A Survey for ALT)
• Title not available (Why is that?)
• Spectral learning of latent-variable PCFGs: algorithms and sample complexity
• Recovering structured probability matrices
• Statistical and computational guarantees for the Baum-Welch algorithm
• Nonparametric estimation of non-exchangeable latent-variable models
• Inference in finite state space non parametric hidden Markov models and applications
• Uniform Chernoff and Dvoretzky-Kiefer-Wolfowitz-type inequalities for Markov chains and related processes
• Approximate minimization of weighted tree automata
• Bisimulation metrics and norms for real-weighted automata
• Hidden Markov models: inverse filtering, belief estimation and privacy protection
• Identifiability of discrete input–output hidden Markov models with external signals
• State-by-state minimax adaptive estimation for nonparametric hidden Markov models
• Title not available (Why is that?)
• Learning hidden Markov models from aggregate observations
• Nonasymptotic control of the MLE for misspecified nonparametric hidden Markov models
• On the Rademacher complexity of weighted automata
• Title not available (Why is that?)
• Sequence classification using third-order moments
• Recognizable series on graphs and hypergraphs
• A Friendly Tutorial on Mean-Field Spin Glass Techniques for Non-Physicists

This page was built for publication: A spectral algorithm for learning hidden Markov models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q439990)