Adaptive low-nonnegative-rank approximation for state aggregation of Markov chains
From MaRDI portal
Publication:5222093
Abstract: This paper develops a low-nonnegative-rank approximation method to identify the state aggregation structure of a finite-state Markov chain under an assumption that the state space can be mapped into a handful of meta-states. The number of meta-states is characterized by the nonnegative rank of the Markov transition matrix. Motivated by the success of the nuclear norm relaxation in low rank minimization problems, we propose an atomic regularizer as a convex surrogate for the nonnegative rank and formulate a convex optimization problem. Because the atomic regularizer itself is not computationally tractable, we instead solve a sequence of problems involving a nonnegative factorization of the Markov transition matrices by using the proximal alternating linearized minimization method. Two methods for adjusting the rank of factorization are developed so that local minima are escaped. One is to append an additional column to the factorized matrices, which can be interpreted as an approximation of a negative subgradient step. The other is to reduce redundant dimensions by means of linear combinations. Overall, the proposed algorithm very likely converges to the global solution. The efficiency and statistical properties of our approach are illustrated on synthetic data. We also apply our state aggregation algorithm on a Manhattan transportation data set and make extensive comparisons with an existing method.
Recommendations
- Learning Markov models via low-rank optimization
- A low-rank spectral method for learning Markov models
- Optimal Kullback-Leibler approximation of Markov chains via nuclear norm regularisation
- A probabilistic algorithm for aggregating vastly undersampled large Markov chains
- Structured nonnegative matrix factorization with applications to hidden Markov realization and clustering
Cites work
- scientific article; zbMATH DE number 1095138 (Why is no real title available?)
- scientific article; zbMATH DE number 6931762 (Why is no real title available?)
- A nonlinear programming algorithm for solving semidefinite programs via low-rank factorization
- Exact matrix completion via convex optimization
- Fast nonnegative matrix factorization: an active-set-like method and comparisons
- Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization
- Low-rank optimization on the cone of positive semidefinite matrices
- Low-rank optimization with trace norm penalty
- Nonnegative Matrix Factorization Based on Alternating Nonnegativity Constrained Least Squares and Active Set Method
- Nonnegative ranks, decompositions, and factorizations of nonnegative matrices
- On the complexity of nonnegative matrix factorization
- Optimal partition and effective dynamics of complex networks
- Projected Gradient Methods for Nonnegative Matrix Factorization
- Proximal alternating linearized minimization for nonconvex and nonsmooth problems
- Reinforcement learning. An introduction
- Solving a low-rank factorization model for matrix completion by a nonlinear successive over-relaxation algorithm
- Statistical Inference about Markov Chains
- The convex geometry of linear inverse problems
Cited in
(6)- Optimal Kullback-Leibler approximation of Markov chains via nuclear norm regularisation
- A probabilistic algorithm for aggregating vastly undersampled large Markov chains
- A low-rank spectral method for learning Markov models
- A low-rank approximation for MDPs via moment coupling
- Learning Markov models via low-rank optimization
- Spectral thresholding for the estimation of Markov chain transition operators
This page was built for publication: Adaptive low-nonnegative-rank approximation for state aggregation of Markov chains
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5222093)
