Skip to content

Bridging Stochastic Flow Maps and Boltzmann Generators with Normalizing Flows

Sep 2026 · arXiv.org · Vol abs/2609.31978 · 0 citations
Computer Science Mathematics

TL;DR

Normalizing Flow Flow Maps (NF$^2$M), which combines the strengths of recent stochastic flow maps with the tractability of classic normalizing flows to build a Boltzmann Generator, and is evaluated on peptide systems, demonstrating improved sampling efficiency and sample quality.

Abstract

Generating independent, equilibrium samples of molecular systems at scale remains a central obstacle in computational statistical mechanics. Boltzmann Generators address this by pairing a generative model with importance sampling to obtain consistent samples from the target distribution. We introduce Normalizing Flow Flow Maps (NF$^2$M), which combines the strengths of recent stochastic flow maps with the tractability of classic normalizing flows to build a Boltzmann Generator. Unlike most methods, which correct the generative model only at the end, NF$^2$M reweighs each denoising transition as generation proceeds, avoiding wasted compute on trajectories that are ultimately discarded. At each denoising step, a conditional normalizing flow proposes clean configurations given the current noisy state (a simpler task than sampling directly from the target) and its exact likelihood enables correcting each proposal toward the true denoising transition of the target Boltzmann distribution. This is in contrast to most existing methods, whose likelihoods are approximate or expensive to evaluate, undermining the statistical reliability of the correction. We establish consistency of the corrected transitions and bound how approximation errors propagate through the sampling chain. We evaluate NF$^2$M on peptide systems, demonstrating improved sampling efficiency and sample quality.

View source

Similar papers

FUND: Density Flow for Sampling Unnormalised Distributions

This work introduces an algorithm for learning Boltzmann distributions that does not require any true samples for training and establishes a new method for sample-free learning of complex physical distributions.

V. Kanaujia, Vipul Arora · 1 citation
#machine learning Preprint Sep 2026

Quenched Ensemble Sampling

Some of the sharpest challenges in sampling from the energy functions of physical systems arise at phase transitions, where the density of states changes abruptly and many sampling algorithms stall. Nested sampling is a particle method that traverses the density of states under a hard energy constraint and is known to...

D. Yallup · 0 citations
#machine learning Preprint Sep 2026

Generative Nested Sampling of Atomistic Thermodynamic Landscapes

This work introduces NS-Flows: a single conditional normalizing flow, conditioned on the NS energy bound and trained on a sliding window of recent live sets, that replaces MCMC by direct parallel draws corrected by importance-weighted rejection resampling, allowing flow training without structured priors or a pre-exist...

A. Coretti, N. Unglert, Sebastian Falkner et al. · 0 citations

Neural Transport Nested Sampling

This work develops a novel sampling algorithm, Neural Transport Nested Sampling (NTNS), which combines the classical strengths of nested sampling with modern neural flow-based methods, and is the first neural sampler to return a calibrated, temperature resolved partition function estimate at this scale.

D. Yallup, Will Handley · 1 citation
#protein folding Sep 2026

Convergence Mechanisms of Generative Models in Molecular Conformational Sampling.

The convergence mechanism is established as a practical design principle for molecular generative sampling, clarifying when stochastic diffusion provides robustness and when deterministic transport requires higher representational capacity.

Nagesh B. E., Jagannath Mondal · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.