Preconditioned One-Step Generative Modeling for Bayesian Inverse Problems in Function Spaces

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cheng, Zilan, Wang, Li-Lian, Wang, Zhongjian
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910275137961984
author Cheng, Zilan
Wang, Li-Lian
Wang, Zhongjian
author_facet Cheng, Zilan
Wang, Li-Lian
Wang, Zhongjian
contents We propose a machine-learning algorithm for Bayesian inverse problems in the function-space regime. Based on one-step generative transport, the method learns an amortized neural operator whose pushforward of a Gaussian source approximates the posterior distribution conditioned on each new observation. We show that white-noise sources are incompatible with the function-space limit, and therefore adopt a prior-aligned GRF as the source. We justify this choice through the Lipschitz regularity of the resulting one-step conditional posterior transport and numerical experiments on linear inverse and PDE-based inverse problems. The method is not distilled from MCMC: it is trained only with prior samples and simulated partial noisy observations. Once trained, it generates a $64\times64$ posterior sample in $\sim 10^{-3}$s, avoiding repeated forward-model evaluations in MCMC and repeated network evaluations in multistep generative samplers while matching key posterior summaries.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14798
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Preconditioned One-Step Generative Modeling for Bayesian Inverse Problems in Function Spaces
Cheng, Zilan
Wang, Li-Lian
Wang, Zhongjian
Machine Learning
Numerical Analysis
We propose a machine-learning algorithm for Bayesian inverse problems in the function-space regime. Based on one-step generative transport, the method learns an amortized neural operator whose pushforward of a Gaussian source approximates the posterior distribution conditioned on each new observation. We show that white-noise sources are incompatible with the function-space limit, and therefore adopt a prior-aligned GRF as the source. We justify this choice through the Lipschitz regularity of the resulting one-step conditional posterior transport and numerical experiments on linear inverse and PDE-based inverse problems. The method is not distilled from MCMC: it is trained only with prior samples and simulated partial noisy observations. Once trained, it generates a $64\times64$ posterior sample in $\sim 10^{-3}$s, avoiding repeated forward-model evaluations in MCMC and repeated network evaluations in multistep generative samplers while matching key posterior summaries.
title Preconditioned One-Step Generative Modeling for Bayesian Inverse Problems in Function Spaces
topic Machine Learning
Numerical Analysis
url https://arxiv.org/abs/2603.14798