A low-rank spectral method for learning Markov models

DOI10.1007/s11590-022-01882-wOpenAlexW4229079376MaRDI QIDQ2679005

Yihong Weng, Shujun Bi, Zhen Yin

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)

Cites Work

• Unnamed Item
• A partial proximal point algorithm for nuclear norm regularized matrix least squares problems
• Max-norm optimization for robust matrix recovery
• Error bounds for analytic systems and their applications
• Error bounds in mathematical programming
• Error bounds for rank constrained optimization problems and applications
• Clustering in block Markov chains
• Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence
• Spectral method and regularized MLE are both optimal for top-\(K\) ranking
• Noisy low-rank matrix completion with general sampling distribution
• Weak Sharp Minima in Mathematical Programming
• Markov Chains
• Variational Analysis
• A survey on error bounds for lower semicontinuous functions
• Global Error Bounds for Convex Conic Problems
• Learning Markov Models Via Low-Rank Optimization
• Spectral State Compression of Markov Processes
• Nonconvex Robust Low-Rank Matrix Recovery
• Adaptive Low-Nonnegative-Rank Approximation for State Aggregation of Markov Chains
• The Spacey Random Walk: A Stochastic Process for Higher-Order Data
• Rank Centrality: Ranking from Pairwise Comparisons

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