Partition Function Estimation under Bounded f-Divergence

TL;DR

This paper provides a comprehensive, information-theoretic analysis of partition function estimation, introducing the integrated coverage profile and establishing tight bounds that unify and extend prior results across various sampling methods.

Contribution

It introduces the integrated coverage profile and characterizes sample complexity for partition function estimation using $f$-divergences, extending classical results to heavy-tailed regimes.

Findings

Tight bounds on sample complexity depending on $f$-divergences.

Unified framework for importance sampling, rejection sampling, and heavy-tailed estimation.

Demonstrates a separation between complexity of approximate sampling and counting.

Abstract

We study the statistical complexity of estimating partition functions given sample access to a proposal distribution and an unnormalized density ratio for a target distribution. While partition function estimation is a classical problem, existing guarantees typically rely on structural assumptions about the domain or model geometry. We instead provide a general, information-theoretic characterization that depends only on the relationship between the proposal and target distributions. Our analysis introduces the integrated coverage profile, a functional that quantifies how much target mass lies in regions where the density ratio is large. We show that integrated coverage tightly characterizes the sample complexity of multiplicative partition function estimation and provide matching lower bounds. We further express these bounds in terms of $f$-divergences, yielding sharp phase transitions depending on the growth rate of f and recovering classical results as a special case while extending to heavy-tailed regimes. Matching lower bounds establish tightness in all regimes. As applications, we derive improved finite-sample guarantees for importance sampling and self-normalized importance sampling, and we show a strict separation between the complexity of approximate sampling and counting under the same divergence constraints. Our results unify and generalize prior analyses of importance sampling, rejection sampling, and heavy-tailed mean estimation, providing a minimal-assumption theory of partition function estimation. Along the way we introduce new technical tools including new connections between coverage and $f$-divergences as well as a generalization of the classical Paley-Zygmund inequality.