Flow perturbation to accelerate Boltzmann sampling

Abstract Flow-based generative models have been employed for Boltzmann sampling tasks, but their application to high-dimensional systems is hindered by the significant computational cost of obtaining the Jacobian of the flow. We introduce a flow perturbation method that bypasses this bottleneck by i...

Full description

Saved in:
Bibliographic Details
Main Authors: Xin Peng, Ang Gao
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-62039-8
Tags: Add Tag
No Tags, Be the first to tag this record!