Flow perturbation to accelerate Boltzmann sampling

Xin Peng and Ang Gao ()
Additional contact information
Xin Peng: Beijing University of Posts and Telecommunications
Ang Gao: Beijing University of Posts and Telecommunications

Nature Communications, 2025, vol. 16, issue 1, 1-14

Abstract: 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 injecting stochastic perturbations into the flow, delivering orders-of-magnitude speed-ups. Unlike the Hutchinson estimator, our approach is inherently unbiased in Boltzmann sampling. Notably, this method significantly accelerates Boltzmann sampling of a Chignolin mutant with all atomic Cartesian coordinates explicitly represented, while delivering more accurate results than the Hutchinson estimator.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-62039-8 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-62039-8

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-62039-8

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().