paper-with-me

홈 › Papers

Taming Score-Based Diffusion Priors for Infinite-Dimensional Nonlinear Inverse Problems

2024-05-24 · Lorenzo Baldassari, Ali Siahkoohi, Josselin Garnier, Knut Solna, Maarten V. de Hoop

This work introduces a sampling method capable of solving Bayesian inverse problems in function space. It does not assume the log-concavity of the likelihood, meaning that it is compatible with nonlinear inverse problems. The method leverages the recently defined infinite-dimensional score-based diffusion models as a learning-based prior, while enabling provable posterior sampling through a Langevin-type MCMC algorithm defined on function spaces. A novel convergence analysis is conducted, inspired by the fixed-point methods established for traditional regularization-by-denoising algorithms and compatible with weighted annealing. The obtained convergence bound explicitly depends on the approximation error of the score; a well-approximated score is essential to obtain a well-approximated posterior. Stylized and PDE-based examples are provided, demonstrating the validity of our convergence analysis. We conclude by presenting a discussion of the method's challenges related to learning the score and computational complexity.

📄 PDF Abstract BibTeX arXiv:2405.15676

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Supervised Guidance Training for Infinite-Dimensional Diffusion Models

2026-01-28 · Elizabeth L. Baker, Alexander Denker, Jes Frellsen arxiv

Score-based diffusion models have recently been extended to infinite-dimensional function spaces, with uses such as inverse problems arising from partial differential equations. In the Bayesian formulation of inverse pro…

Multilevel Diffusion: Infinite Dimensional Score-Based Diffusion Models for Image Generation

2023-03-08 · Paul Hagemann, Sophie Mildenberger, Lars Ruthotto, Gabriele Steidl 외

Score-based diffusion models (SBDM) have recently emerged as state-of-the-art approaches for image generation. Existing SBDMs are typically formulated in a finite-dimensional setting, where images are considered as tenso…

Image Generation

Geometric Neural Diffusion Processes

2023-07-11 · NeurIPS 2023 11 · Emile Mathieu, Vincent Dutordoir, Michael J. Hutchinson, Valentin De Bortoli 외

Denoising diffusion models have proven to be a flexible and effective paradigm for generative modelling. Their recent extension to infinite dimensional Euclidean spaces has allowed for the modelling of stochastic process…

Denoising

Scalable diffusion posterior sampling in infinite-dimensional inverse problems

2024-05-24 · Fabian Schneider, Duc-Lam Duong, Matti Lassas, Maarten V. de Hoop 외

Score-based diffusion models (SDMs) have emerged as a powerful tool for sampling from the posterior distribution in Bayesian inverse problems. However, existing methods often require multiple evaluations of the forward m…

Conditioning non-linear and infinite-dimensional diffusion processes

2024-02-02 · Elizabeth Louise Baker, Gefan Yang, Michael L. Severinsen, Christy Anna Hipsley 외

Generative diffusion models and many stochastic models in science and engineering naturally live in infinite dimensions before discretisation. To incorporate observed data for statistical and learning tasks, one needs to…

Time SeriesTime Series Analysis