Asymptotically unbiased estimation of physical observables with neural samplers

Kim A. Nicoli, Shinichi Nakajima, Nils Strodthoff, Wojciech Samek, Klaus Robert Müller, Pan Kessel

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

We propose a general framework for the estimation of observables with generative neural samplers focusing on modern deep generative neural networks that provide an exact sampling probability. In this framework, we present asymptotically unbiased estimators for generic observables, including those that explicitly depend on the partition function such as free energy or entropy, and derive corresponding variance estimators. We demonstrate their practical applicability by numerical experiments for the two-dimensional Ising model which highlight the superiority over existing methods. Our approach greatly enhances the applicability of generative neural samplers to real-world physical systems.

Original languageEnglish
Article number023304
JournalPhysical Review E
Volume101
Issue number2
DOIs
Publication statusPublished - 2020 Feb
Externally publishedYes

ASJC Scopus subject areas

  • Statistical and Nonlinear Physics
  • Statistics and Probability
  • Condensed Matter Physics

Cite this

Nicoli, K. A., Nakajima, S., Strodthoff, N., Samek, W., Müller, K. R., & Kessel, P. (2020). Asymptotically unbiased estimation of physical observables with neural samplers. Physical Review E, 101(2), [023304]. https://doi.org/10.1103/PhysRevE.101.023304