Work

Conditional sampling within generative diffusion models

Year: 2025

Type: review

Abstract: Generative diffusions are a powerful class of Monte Carlo samplers that leverage bridging Markov processes to approximate complex, high-dimensional distributions, such as those found in image processing and language models. Despite their success in these domains, an important open challenge remains: extending these techniques to sample from conditional distributions, as required in, for example, Bayesian inverse problems. In this paper, we present a comprehensive review of existing computational approaches to conditional sampling within generative diffusion models. Specifically, we highlight key methodologies that either utilize the joint distribution, or rely on (pre-trained) marginal distributions with explicit likelihoods, to construct conditional generative samplers.This article is part of the theme issue 'Generative modelling meets Bayesian inference: a new paradigm for inverse problems'.

Source: Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences

DOI: 10.1098/rsta.2024.0329

Authors: Zheng Zhao, Ziwei Luo, Jens Sjölund, Thomas Schön

Institutions: Linköping University, Uppsala University

Language: English

Topic: Markov Chains and Monte Carlo Methods

Subfield: Statistics and Probability

Field: Mathematics

Domain: Physical Sciences

Open Access status: hybrid

Funders: Knut och Alice Wallenbergs Stiftelse, Vetenskapsrådet

Award: Deep probabilistic regression - new models and learning algorithms