A low-rank spectral method for learning Markov models

DOI10.1007/S11590-022-01882-WMaRDI QIDQ2679005zbMATH OpenOpenAlexFDO

Authors Shujun Bi, Zhen Yin, Yihong Weng

Publication date 18 January 2023

Published in Optimization Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s11590-022-01882-w

zbMATH Keywords

Lipschitzian error boundlow-rank Markov chainlow-rank spectral estimatorstatistical upper bound

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Recommendations

• Learning Markov models via low-rank optimization
• Spectral thresholding for the estimation of Markov chain transition operators
• Adaptive low-nonnegative-rank approximation for state aggregation of Markov chains
• Statistical estimation of ergodic Markov chain kernel over discrete state space
• Tensor train spectral method for learning of hidden Markov models (HMM)

Cites work

• A partial proximal point algorithm for nuclear norm regularized matrix least squares problems
• A survey on error bounds for lower semicontinuous functions
• Adaptive low-nonnegative-rank approximation for state aggregation of Markov chains
• Clustering in block Markov chains
• Error bounds for analytic systems and their applications
• Error bounds for rank constrained optimization problems and applications
• Error bounds in mathematical programming
• Global Error Bounds for Convex Conic Problems
• Learning Markov models via low-rank optimization
• Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence
• Markov Chains
• Markov chains and mixing times. With a chapter on ``Coupling from the past by James G. Propp and David B. Wilson.
• Max-norm optimization for robust matrix recovery
• Noisy low-rank matrix completion with general sampling distribution
• Nonconvex Robust Low-Rank Matrix Recovery
• Rank Centrality: Ranking from Pairwise Comparisons
• Spectral State Compression of Markov Processes
• Spectral method and regularized MLE are both optimal for top-\(K\) ranking
• The Spacey Random Walk: A Stochastic Process for Higher-Order Data
• Variational Analysis
• Weak Sharp Minima in Mathematical Programming

Cited in

(5)

• Low-rank tensor methods for Markov chains with applications to tumor progression models
• Learning Markov models via low-rank optimization
• Adaptive low-nonnegative-rank approximation for state aggregation of Markov chains
• scientific article; zbMATH DE number 6781356 (Why is no real title available?)
• Spectral thresholding for the estimation of Markov chain transition operators

This page was built for publication: A low-rank spectral method for learning Markov models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2679005)