The Bethe and Sinkhorn Permanents of Low Rank Matrices and Implications for Profile Maximum Likelihood

TL;DR

This paper develops polynomial-time algorithms for profile maximum likelihood estimation in discrete distributions, leveraging new bounds on Bethe and Sinkhorn permanents, leading to improved approximation guarantees and broader applicability.

Contribution

The paper introduces new bounds on Bethe and Sinkhorn permanents for low-rank matrices, enabling better polynomial-time approximation algorithms for profile maximum likelihood estimation.

Findings

Achieves approximation factor of exp(-O(√n log n)) for PML, improving previous bounds.

Provides new bounds on Bethe and Sinkhorn permanents for matrices with low non-negative rank.

Establishes a connection between convex relaxations and Bethe/Sinkhorn approximations.

Abstract

In this paper we consider the problem of computing the likelihood of the profile of a discrete distribution, i.e., the probability of observing the multiset of element frequencies, and computing a profile maximum likelihood (PML) distribution, i.e., a distribution with the maximum profile likelihood. For each problem we provide polynomial time algorithms that given $n$ i.i.d.\ samples from a discrete distribution, achieve an approximation factor of $\exp\left(-O(\sqrt{n} \log n) \right)$, improving upon the previous best-known bound achievable in polynomial time of $\exp(-O(n^{2/3} \log n))$ (Charikar, Shiragur and Sidford, 2019). Through the work of Acharya, Das, Orlitsky and Suresh (2016), this implies a polynomial time universal estimator for symmetric properties of discrete distributions in a broader range of error parameter. We achieve these results by providing new bounds on the quality of approximation of the Bethe and Sinkhorn permanents (Vontobel, 2012 and 2014). We show that each of these are $\exp(O(k \log(N/k)))$ approximations to the permanent of $N \times N$ matrices with non-negative rank at most $k$, improving upon the previous known bounds of $\exp(O(N))$. To obtain our results on PML, we exploit the fact that the PML objective is proportional to the permanent of a certain Vandermonde matrix with $\sqrt{n}$ distinct columns, i.e. with non-negative rank at most $\sqrt{n}$. As a by-product of our work we establish a surprising connection between the convex relaxation in prior work (CSS19) and the well-studied Bethe and Sinkhorn approximations.