English

Information Criterion for Boltzmann Approximation Problems

Methodology 2020-10-08 v3

Abstract

This paper considers the problem of approximating a density when it can be evaluated up to a normalizing constant at a limited number of points. We call this problem the Boltzmann approximation (BA) problem. The BA problem is ubiquitous in statistics, such as approximating a posterior density for Bayesian inference and estimating an optimal density for importance sampling. Approximating the density with a parametric model can be cast as a model selection problem. This problem cannot be addressed with traditional approaches that maximize the (marginal) likelihood of a model, for example, using the Akaike information criterion (AIC) or Bayesian information criterion (BIC). We instead aim to minimize the cross-entropy that gauges the deviation of a parametric model from the target density. We propose a novel information criterion called the cross-entropy information criterion (CIC) and prove that the CIC is an asymptotically unbiased estimator of the cross-entropy (up to a multiplicative constant) under some regularity conditions. We propose an iterative method to approximate the target density by minimizing the CIC. We demonstrate that the proposed method selects a parametric model that well approximates the target density.

Keywords

Cite

@article{arxiv.1704.04315,
  title  = {Information Criterion for Boltzmann Approximation Problems},
  author = {Youngjun Choe and Yen-Chi Chen and Nick Terry},
  journal= {arXiv preprint arXiv:1704.04315},
  year   = {2020}
}

Comments

67 pages, 5 figures

R2 v1 2026-06-22T19:17:12.884Z