← Back to all news
arXiv AI By Jitao Xu, Nobuo Sato, Yaohang Li

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

Read the original on arXiv AI →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Sep 4

Learning Informative Prior with Infinite-Dimensional Continuous Normalizing Flow for Bayesian Inverse Problem

The paper introduces a continuous normalizing flow model for infinite-dimensional Bayesian inference in inverse problems governed by partial differential equations. By defining a neural ordinary differential equation in an infinite-dimensional Hilbert space, a simple reference measure is transformed into a complex prior that captures prior information. The authors establish a theoretical framework for well-posedness, present training methods for two data settings, and provide sampling algorithms, applying the approach to smooth, scattering, and heat conduction inverse problems with supporting numerical experiments.

By Yang Zhao, Junxiong Jia, Tao Zhou
More like this →
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
diffusion
More like this →