Improving the convergence of Markov chains via permutations and projections

TL;DR

This paper introduces permutation-based projections to enhance Markov chain convergence, demonstrating improved mixing times through theoretical analysis and practical examples, including reductions from exponential to polynomial and logarithmic times.

Contribution

It proposes a novel permutation and projection framework for Markov chain convergence, with theoretical conditions and practical algorithms showing significant improvements over traditional methods.

Findings

Projection samplers outperform Metropolis-Hastings in bimodal distributions.

Mixture of permuted chains achieves logarithmic mixing time.

Numerical experiments confirm improved convergence in physics models.

Abstract

This paper aims at improving the convergence to equilibrium of finite ergodic Markov chains via permutations and projections. First, we prove that a specific mixture of permuted Markov chains arises naturally as a projection under the KL divergence or the squared-Frobenius norm. We then compare various mixing properties of the mixture with other competing Markov chain samplers and demonstrate that it enjoys improved convergence. This geometric perspective motivates us to propose samplers based on alternating projections to combine different permutations and to analyze their rate of convergence. We give necessary, and under some additional assumptions also sufficient, conditions for the projection to achieve stationarity in the limit in terms of the trace of the transition matrix. We proceed to discuss tuning strategies of the projection samplers when these permutations are viewed as parameters. Along the way, we reveal connections between the mixture and a Markov chain Sylvester's equation as well as assignment problems, and highlight how these can be used to understand and improve Markov chain mixing. We provide two examples as illustrations. In the first example, the projection sampler (with a suitable choice of the permutation) improves upon Metropolis-Hastings in a discrete bimodal distribution with a reduced relaxation time from exponential to polynomial in the system size, while in the second example, the mixture of permuted Markov chain yields a mixing time that is logarithmic in system size (with high probability under random permutation), compared to a linear mixing time in the Diaconis-Holmes-Neal sampler. Finally, we provide numerical experiments on simple statistical physics models to illustrate the improved mixing performance of the proposed projection samplers over standard Metropolis-Hastings.