Provable Mixed-Noise Learning with Flow-Matching

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hagemann, Paul, Gruhlke, Robert, Stankewitz, Bernhard, Schillings, Claudia, Steidl, Gabriele
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909849984434176
author Hagemann, Paul
Gruhlke, Robert
Stankewitz, Bernhard
Schillings, Claudia
Steidl, Gabriele
author_facet Hagemann, Paul
Gruhlke, Robert
Stankewitz, Bernhard
Schillings, Claudia
Steidl, Gabriele
contents We study Bayesian inverse problems with mixed noise, modeled as a combination of additive and multiplicative Gaussian components. While traditional inference methods often assume fixed or known noise characteristics, real-world applications, particularly in physics and chemistry, frequently involve noise with unknown and heterogeneous structure. Motivated by recent advances in flow-based generative modeling, we propose a novel inference framework based on conditional flow matching embedded within an Expectation-Maximization (EM) algorithm to jointly estimate posterior samplers and noise parameters. To enable high-dimensional inference and improve scalability, we use simulation-free ODE-based flow matching as the generative model in the E-step of the EM algorithm. We prove that, under suitable assumptions, the EM updates converge to the true noise parameters in the population limit of infinite observations. Our numerical results illustrate the effectiveness of combining EM inference with flow matching for mixed-noise Bayesian inverse problems.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18122
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Provable Mixed-Noise Learning with Flow-Matching
Hagemann, Paul
Gruhlke, Robert
Stankewitz, Bernhard
Schillings, Claudia
Steidl, Gabriele
Machine Learning
Optimization and Control
We study Bayesian inverse problems with mixed noise, modeled as a combination of additive and multiplicative Gaussian components. While traditional inference methods often assume fixed or known noise characteristics, real-world applications, particularly in physics and chemistry, frequently involve noise with unknown and heterogeneous structure. Motivated by recent advances in flow-based generative modeling, we propose a novel inference framework based on conditional flow matching embedded within an Expectation-Maximization (EM) algorithm to jointly estimate posterior samplers and noise parameters. To enable high-dimensional inference and improve scalability, we use simulation-free ODE-based flow matching as the generative model in the E-step of the EM algorithm. We prove that, under suitable assumptions, the EM updates converge to the true noise parameters in the population limit of infinite observations. Our numerical results illustrate the effectiveness of combining EM inference with flow matching for mixed-noise Bayesian inverse problems.
title Provable Mixed-Noise Learning with Flow-Matching
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2508.18122