Optimal Kullback-Leibler Aggregation via Spectral Theory of Markov Chains

DOI10.1109/TAC.2011.2141350MaRDI QIDQ5347914zbMATH OpenFDO

Authors Kun Deng, Prashant G. Mehta, Sean P. Meyn

Publication date 25 August 2017

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/TAC.2011.2141350

Mathematics Subject Classification ID

Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Statistical aspects of information-theoretic topics (62B10) System structure simplification (93B11) Eigenvalue problems (93B60)

Recommendations

• A Generalized Framework For Kullback–Leibler Markov Aggregation
• Optimal Kullback-Leibler aggregation in mixture density estimation by maximum likelihood
• Optimal Kullback-Leibler approximation of Markov chains via nuclear norm regularisation
• On the Convergence of an Efficient Algorithm for Kullback–Leibler Approximation of Spectral Densities
• Optimal exponential bounds for aggregation of estimators for the Kullback-Leibler loss
• Optimal measures and Markov transition kernels
• Estimation of finite probabilities via aggregation of Markov chains
• Optimal Kullback–Leibler Aggregation via Information Bottleneck
• An algorithm approach to bounding aggregations of multidimensional Markov chains
• Optimal aggregation of components for the solution of Markov regenerative processes

Cited in

(11)

• The average cost of Markov chains subject to total variation distance uncertainty
• Synwalk: community detection via random walk modelling
• Approximating a diffusion by a finite-state hidden Markov model
• A sufficient condition for a unique invariant distribution of a higher-order Markov chain
• Optimal Kullback-Leibler approximation of Markov chains via nuclear norm regularisation
• Oja's algorithm for graph clustering, Markov spectral decomposition, and risk sensitive control
• Structure-preserving model reduction of nonlinear building thermal models
• Reduced-order modeling of large-scale network systems
• Learning Markov models via low-rank optimization
• A mixed integer linear program to compress transition probability matrices in Markov chain bootstrapping
• Approximate lumpability for Markovian agent-based models using local symmetries

This page was built for publication: Optimal Kullback-Leibler Aggregation via Spectral Theory of Markov Chains

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5347914)