Uncertainty in AI-driven Monte Carlo simulations

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Tzivrailis, Dimitrios, Rosso, Alberto, Kawasaki, Eiji
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915367754924032
author Tzivrailis, Dimitrios
Rosso, Alberto
Kawasaki, Eiji
author_facet Tzivrailis, Dimitrios
Rosso, Alberto
Kawasaki, Eiji
contents In the study of complex systems, evaluating physical observables often requires sampling representative configurations via Monte Carlo techniques. These methods rely on repeated evaluations of the system's energy and force fields, which can become computationally expensive. To accelerate these simulations, deep learning models are increasingly employed as surrogate functions to approximate the energy landscape or force fields. However, such models introduce epistemic uncertainty in their predictions, which may propagate through the sampling process and affect the system's macroscopic behavior. In our work, we present the Penalty Ensemble Method (PEM) to quantify epistemic uncertainty and mitigate its impact on Monte Carlo sampling. Our approach introduces an uncertainty-aware modification of the Metropolis acceptance rule, which increases the rejection probability in regions of high uncertainty, thereby enhancing the reliability of the simulation outcomes.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14594
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uncertainty in AI-driven Monte Carlo simulations
Tzivrailis, Dimitrios
Rosso, Alberto
Kawasaki, Eiji
Disordered Systems and Neural Networks
Statistical Mechanics
Machine Learning
In the study of complex systems, evaluating physical observables often requires sampling representative configurations via Monte Carlo techniques. These methods rely on repeated evaluations of the system's energy and force fields, which can become computationally expensive. To accelerate these simulations, deep learning models are increasingly employed as surrogate functions to approximate the energy landscape or force fields. However, such models introduce epistemic uncertainty in their predictions, which may propagate through the sampling process and affect the system's macroscopic behavior. In our work, we present the Penalty Ensemble Method (PEM) to quantify epistemic uncertainty and mitigate its impact on Monte Carlo sampling. Our approach introduces an uncertainty-aware modification of the Metropolis acceptance rule, which increases the rejection probability in regions of high uncertainty, thereby enhancing the reliability of the simulation outcomes.
title Uncertainty in AI-driven Monte Carlo simulations
topic Disordered Systems and Neural Networks
Statistical Mechanics
Machine Learning
url https://arxiv.org/abs/2506.14594