Parameter estimation for Gibbs distributions
Abstract
We consider Gibbs distributions, which are families of probability distributions over a discrete space with probability mass function of the form for in an interval and . The partition function is the normalization factor . Two important parameters of these distributions are the log partition ratio and the counts . These are correlated with system parameters in a number of physical applications and sampling algorithms. Our first main result is to estimate the counts using roughly samples for general Gibbs distributions and samples for integer-valued distributions (ignoring some second-order terms and parameters), and we show this is optimal up to logarithmic factors. We illustrate with improved algorithms for counting connected subgraphs, independent sets, and perfect matchings. As a key subroutine, we also develop algorithms to compute the partition function using samples for general Gibbs distributions and using samples for integer-valued distributions.
Keywords
Cite
@article{arxiv.2007.10824,
title = {Parameter estimation for Gibbs distributions},
author = {David G. Harris and Vladimir Kolmogorov},
journal= {arXiv preprint arXiv:2007.10824},
year = {2025}
}
Comments
This is a longer version which extends two previous papers "A Faster Approximation Algorithm for the Gibbs Partition Function" (arXiv:1608.04223), published in COLT 2018, and "Parameter estimation for Gibbs distributions" published in ICALP 2023