Information-theoretic minimax and submodular optimization algorithms for multivariate Markov chains

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lai, Zheyuan, Choi, Michael C. H.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918339257827328
author Lai, Zheyuan
Choi, Michael C. H.
author_facet Lai, Zheyuan
Choi, Michael C. H.
contents We study an information-theoretic minimax problem for finite multivariate Markov chains on $d$-dimensional product state spaces. Given a family $\mathcal B=\{P_1,\ldots,P_n\}$ of $π$-stationary transition matrices and a class $\mathcal F = \mathcal{F}(\mathbf{S})$ of factorizable models induced by a partition $\mathbf S$ of the coordinate set $[d]$, we seek to minimize the worst-case information loss by analyzing $$\min_{Q\in\mathcal F}\max_{P\in\mathcal B} D_{\mathrm{KL}}^π(P\|Q),$$ where $D_{\mathrm{KL}}^π(P\|Q)$ is the $π$-weighted KL divergence from $Q$ to $P$. We recast the above minimax problem into concave maximization over the $n$-probability-simplex via strong duality and Pythagorean identities that we derive. This leads us to formulate an information-theoretic game and show that a mixed strategy Nash equilibrium always exists; and propose a projected subgradient algorithm to approximately solve the minimax problem with provable guarantee. By transforming the minimax problem into an orthant submodular function in $\mathbf{S}$, this motivates us to consider a max-min-max submodular optimization problem and investigate a two-layer subgradient-greedy procedure to approximately solve this generalization. Numerical experiments for Markov chains on the Curie-Weiss and Bernoulli-Laplace models illustrate the practicality of these proposed algorithms and reveals sparse optimal structures in these examples.
format Preprint
id arxiv_https___arxiv_org_abs_2511_00769
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Information-theoretic minimax and submodular optimization algorithms for multivariate Markov chains
Lai, Zheyuan
Choi, Michael C. H.
Probability
Optimization and Control
Computation
49J35, 60J10, 60J22, 90C27, 91A05, 94A15, 94A17
We study an information-theoretic minimax problem for finite multivariate Markov chains on $d$-dimensional product state spaces. Given a family $\mathcal B=\{P_1,\ldots,P_n\}$ of $π$-stationary transition matrices and a class $\mathcal F = \mathcal{F}(\mathbf{S})$ of factorizable models induced by a partition $\mathbf S$ of the coordinate set $[d]$, we seek to minimize the worst-case information loss by analyzing $$\min_{Q\in\mathcal F}\max_{P\in\mathcal B} D_{\mathrm{KL}}^π(P\|Q),$$ where $D_{\mathrm{KL}}^π(P\|Q)$ is the $π$-weighted KL divergence from $Q$ to $P$. We recast the above minimax problem into concave maximization over the $n$-probability-simplex via strong duality and Pythagorean identities that we derive. This leads us to formulate an information-theoretic game and show that a mixed strategy Nash equilibrium always exists; and propose a projected subgradient algorithm to approximately solve the minimax problem with provable guarantee. By transforming the minimax problem into an orthant submodular function in $\mathbf{S}$, this motivates us to consider a max-min-max submodular optimization problem and investigate a two-layer subgradient-greedy procedure to approximately solve this generalization. Numerical experiments for Markov chains on the Curie-Weiss and Bernoulli-Laplace models illustrate the practicality of these proposed algorithms and reveals sparse optimal structures in these examples.
title Information-theoretic minimax and submodular optimization algorithms for multivariate Markov chains
topic Probability
Optimization and Control
Computation
49J35, 60J10, 60J22, 90C27, 91A05, 94A15, 94A17
url https://arxiv.org/abs/2511.00769