English

Learning Markov models via low-rank optimization

Methodology 2020-11-30 v2 Machine Learning

Abstract

Modeling unknown systems from data is a precursor of system optimization and sequential decision making. In this paper, we focus on learning a Markov model from a single trajectory of states. Suppose that the transition model has a small rank despite of having a large state space, meaning that the system admits a low-dimensional latent structure. We show that one can estimate the full transition model accurately using a trajectory of length that is proportional to the total number of states. We propose two maximum likelihood estimation methods: a convex approach with nuclear-norm regularization and a nonconvex approach with rank constraint. We explicitly derive the statistical rates of both estimators in terms of the Kullback-Leiber divergence and the 2\ell_2 error and also establish a minimax lower bound to assess the tightness of these rates. For computing the nonconvex estimator, we develop a novel DC (difference of convex function) programming algorithm that starts with the convex M-estimator and then successively refines the solution till convergence. Empirical experiments demonstrate consistent superiority of the nonconvex estimator over the convex one.

Keywords

Cite

@article{arxiv.1907.00113,
  title  = {Learning Markov models via low-rank optimization},
  author = {Ziwei Zhu and Xudong Li and Mengdi Wang and Anru Zhang},
  journal= {arXiv preprint arXiv:1907.00113},
  year   = {2020}
}

Comments

52 pages, 4 figures. arXiv admin note: text overlap with arXiv:1804.00795

R2 v1 2026-06-23T10:07:19.036Z