Saved in:
Bibliographic Details
Main Authors: Yu, Zichao, Li, Ming, Zhang, Wenyi, Zou, Difan, Gao, Weiguo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.20227
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914285870907392
author Yu, Zichao
Li, Ming
Zhang, Wenyi
Zou, Difan
Gao, Weiguo
author_facet Yu, Zichao
Li, Ming
Zhang, Wenyi
Zou, Difan
Gao, Weiguo
contents Inferring physical fields from sparse observations while strictly satisfying partial differential equations (PDEs) is a fundamental challenge in computational physics. Recently, deep generative models offer powerful data-driven priors for such inverse problems, yet existing methods struggle to enforce hard physical constraints without costly retraining or disrupting the learned generative prior. Consequently, there is a critical need for a sampling mechanism that can reconcile strict physical consistency and observational fidelity with the statistical structure of the pre-trained prior. To this end, we present ProFlow, a proximal guidance framework for zero-shot physics-consistent sampling, defined as inferring solutions from sparse observations using a fixed generative prior without task-specific retraining. The algorithm employs a rigorous two-step scheme that alternates between: (\romannumeral1) a terminal optimization step, which projects the flow prediction onto the intersection of the physically and observationally consistent sets via proximal minimization; and (\romannumeral2) an interpolation step, which maps the refined state back to the generative trajectory to maintain consistency with the learned flow probability path. This procedure admits a Bayesian interpretation as a sequence of local maximum a posteriori (MAP) updates. Comprehensive benchmarks on Poisson, Helmholtz, Darcy, and viscous Burgers' equations demonstrate that ProFlow achieves superior physical and observational consistency, as well as more accurate distributional statistics, compared to state-of-the-art diffusion- and flow-based baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2601_20227
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ProFlow: Zero-Shot Physics-Consistent Sampling via Proximal Flow Guidance
Yu, Zichao
Li, Ming
Zhang, Wenyi
Zou, Difan
Gao, Weiguo
Machine Learning
Artificial Intelligence
Numerical Analysis
Inferring physical fields from sparse observations while strictly satisfying partial differential equations (PDEs) is a fundamental challenge in computational physics. Recently, deep generative models offer powerful data-driven priors for such inverse problems, yet existing methods struggle to enforce hard physical constraints without costly retraining or disrupting the learned generative prior. Consequently, there is a critical need for a sampling mechanism that can reconcile strict physical consistency and observational fidelity with the statistical structure of the pre-trained prior. To this end, we present ProFlow, a proximal guidance framework for zero-shot physics-consistent sampling, defined as inferring solutions from sparse observations using a fixed generative prior without task-specific retraining. The algorithm employs a rigorous two-step scheme that alternates between: (\romannumeral1) a terminal optimization step, which projects the flow prediction onto the intersection of the physically and observationally consistent sets via proximal minimization; and (\romannumeral2) an interpolation step, which maps the refined state back to the generative trajectory to maintain consistency with the learned flow probability path. This procedure admits a Bayesian interpretation as a sequence of local maximum a posteriori (MAP) updates. Comprehensive benchmarks on Poisson, Helmholtz, Darcy, and viscous Burgers' equations demonstrate that ProFlow achieves superior physical and observational consistency, as well as more accurate distributional statistics, compared to state-of-the-art diffusion- and flow-based baselines.
title ProFlow: Zero-Shot Physics-Consistent Sampling via Proximal Flow Guidance
topic Machine Learning
Artificial Intelligence
Numerical Analysis
url https://arxiv.org/abs/2601.20227