Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Asymptotically unbiased estimation of physical observables with neural samplers

Authors
Nicoli, Kim A.Nakajima, ShinichiStrodthoff, NilsSamek, WojciechMueller, Klaus-RobertKessel, Pan
Issue Date
10-2월-2020
Publisher
AMER PHYSICAL SOC
Citation
PHYSICAL REVIEW E, v.101, no.2
Indexed
SCIE
SCOPUS
Journal Title
PHYSICAL REVIEW E
Volume
101
Number
2
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/57678
DOI
10.1103/PhysRevE.101.023304
ISSN
2470-0045
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.
Files in This Item
There are no files associated with this item.
Appears in
Collections
Graduate School > Department of Artificial Intelligence > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetrics

Total Views & Downloads

BROWSE