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

04/06/2020
by   Nima Anari, et al.
8

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 (-O(√(n)log n) ), improving upon the previous best-known bound achievable in polynomial time of (-O(n^2/3log 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 (O(k log(N/k))) approximations to the permanent of N × N matrices with non-negative rank at most k, improving upon the previous known bounds of (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 √(n) distinct columns, i.e. with non-negative rank at most √(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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

05/21/2019

Efficient Profile Maximum Likelihood for Universal Symmetric Property Estimation

Estimating symmetric properties of a distribution, e.g. support size, co...
11/05/2020

Instance Based Approximations to Profile Maximum Likelihood

In this paper we provide a new efficient algorithm for approximately com...
07/18/2019

A Polynomial Time Algorithm for Log-Concave Maximum Likelihood via Locally Exponential Families

We consider the problem of computing the maximum likelihood multivariate...
04/07/2020

The Optimality of Profile Maximum Likelihood in Estimating Sorted Discrete Distributions

A striking result of [Acharya et al. 2017] showed that to estimate symme...
07/11/2012

On Modeling Profiles instead of Values

We consider the problem of estimating the distribution underlying an obs...
10/30/2019

Constrained Polynomial Likelihood

Starting from a distribution z, we develop a non-negative polynomial min...
07/15/2021

Computing Permanents on a Trellis

The problem of computing the permanent of a matrix has attracted interes...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.