arXiv Machine Learning

Machine Learning for Inverse Problems and Data Assimilation

arXiv:2410. 10523v3 Announce Type: replace-cross Abstract: The aim of this book is to demonstrate the potential for ideas in machine learning to impact on the fields of inverse problems and data assimilation.

arXiv Computer Vision
Sep 2

Diffusion Based Unpaired Data Learning for Inverse Problems

The paper introduces LUD-DIF, a diffusion-based method that solves inverse problems using unpaired data. By deriving the evidence lower bound of the joint distribution and decoupling it into two independent diffusion processes under a weak‑coupling assumption, the authors provide a variational inference framework, a loss function, and an error‑bound analysis. Experiments show that LUD‑DIF performs well across multiple image inverse problems, demonstrating its effectiveness and generalization in unpaired settings.

By Chenglong Bao, Yiming Dang, Chenguang Duan, Yuling Jiao, Defeng Sun
arXiv Machine Learning
1d ago

Auto-differentiable data assimilation: Co-learning of states, dynamics, and filtering algorithms

The paper presents a framework called auto‑differentiable filtering that jointly learns the state, dynamics, and filtering algorithm parameters in data assimilation. It uses a loss function that allows gradient‑based optimization from partial, noisy observations via auto‑differentiation. Experiments demonstrate the method on diverse dynamical systems, including aerospace, atmospheric, biological, and geophysical models, and the authors offer guidelines for tailoring the framework to specific observation models, accuracy needs, and computational budgets.

By Melissa Adrian, Daniel Sanz-Alonso, Rebecca Willett
arXiv Machine Learning
Jul 8

A Gibbs posterior sampler for inverse problem based on prior diffusion model

arXiv:2602. 11059v2 Announce Type: replace-cross Abstract: This paper addresses the issue of inversion in cases where (1) the observation system is modeled by a linear transformation and additive error, (2) the problem is ill-posed and regularization relies on a Bayesian strategy, (3)~the prior is modeled by a diffusion process adjusted on an available large set of examples.

By Jean-Fran\c{c}ois Giovannelli
arXiv AI
Aug 28

Active Diffusion-Based Inference for Ill-Posed Inverse Problems under Incomplete Priors

The paper introduces an active diffusion-based inverse problem solver that trains a diffusion model to map between parameter and observable spaces. By iteratively detecting and correcting model misspecification through posterior uncertainty, the method can discover and learn the correct parameter region even when initial training bounds exclude the true parameters. The authors demonstrate the solver on a toy inverse problem with infinite solutions and on parameterizing quantum correlation functions for a Quantum Chromodynamics analysis of nucleon structure.

By Jitao Xu, Nobuo Sato, Yaohang Li
arXiv Statistics ML
Oct 26

Stochastic Inverse Problem: stability, regularization and Wasserstein gradient flow

The paper investigates stochastic inverse problems where the goal is to recover a probability distribution of an unknown parameter that explains observed data. It examines direct inversion, a variational formulation with regularization, and optimization via Wasserstein gradient flows, highlighting parallels and differences with deterministic inverse problems. A key finding is that the choice of metric—both in the loss function and during optimization—strongly influences stability and the optimizer’s properties.

By Qin Li, Maria Oprea, Li Wang, Yunan Yang
arXiv Machine Learning
Aug 31

Examining the robustness of Physics-Informed Neural Networks to noise for Inverse Problems

The paper evaluates the robustness of Physics‑Informed Neural Networks (PINNs) against noisy data in inverse problems, comparing them to a finite element method (FEM) plus optimizer baseline. Experiments on viscosity identification in 1D Burgers’ equation and 2D/3D Taylor‑Green Vortex with additive Gaussian noise show that PINNs, while requiring less human expertise, are outperformed by the traditional FEM approach in accuracy (e.g., RMSE 0.01 vs. 0.0013 for 2D Taylor‑Green with σ=1). PINNs do, however, exhibit better scaling with problem complexity, and the study highlights specific training failures that must be addressed for PINNs to become more competitive.

By Aleksandra Jekic, Afroditi Natsaridou, Signe Riemer-S{\o}rensen, Helge Langseth, Odd Erik Gundersen