Statistical and Computational Guarantees for the Baum-Welch Algorithm

zbMath1442.62192arXiv1512.08269MaRDI QIDQ4637049

Martin J. Wainwright, Sivaraman Balakrishnan, Fanny Yang

Publication date: 17 April 2018

Full work available at URL: https://arxiv.org/abs/1512.08269

zbMATH Keywords

EM algorithmhidden Markov modelsnon-convex optimizationgraphical modelsBaum-Welch algorithm

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Markov processes: estimation; hidden Markov models (62M05) Probabilistic graphical models (62H22)

Related Items

Sharp global convergence guarantees for iterative nonconvex optimization with random data

Cites Work

• A spectral algorithm for learning hidden Markov models
• Statistical guarantees for the EM algorithm: from population to sample-based analysis
• Probability in Banach spaces. Isoperimetry and processes
• A spectral algorithm for learning mixture models
• On the convergence properties of the EM algorithm
• Rates of convergence for empirical processes of stationary mixing sequences
• A note on uniform laws of averages for dependent processes
• Asymptotic normality of the maximum-likelihood estimator for general hidden Markov models
• Weak convergence and empirical processes. With applications to statistics
• Learning mixtures of spherical gaussians
• On Talagrand's deviation inequalities for product measures
• Graphical Models, Exponential Families, and Variational Inference
• Biological Sequence Analysis
• Factor graphs and the sum-product algorithm
• Statistical Inference for Probabilistic Functions of Finite State Markov Chains
• 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