# Diffusion Schrodinger Bridges for Bayesian Computation

STATISTICAL SCIENCE（2024）

Abstract

Denoising diffusion models are a novel class of generative models that have recently become extremely popular in machine learning. In this paper, we describe how such ideas can also be used to sample from posterior distributions and, more generally, any target distribution whose density is known up to a normalizing constant. The key idea is to consider a forward "noising" diffusion initialized at the target distribution, which "transports" this latter to a normal distribution for long diffusion times. The time reversal of this process, the "denoising" diffusion, thus "transports" the normal distribution to the target distribution and can be approximated so as to sample from the target. To accelerate simulation, we show how one can introduce and approximate a Schrodinger bridge between these two distributions, that is, a diffusion which transports the normal to the target in finite time.

MoreTranslated text

Key words

Optimal transport,Schrodinger bridge,score matching,stochastic differential equation,time reversal

AI Read Science

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper

Chat Paper

Summary is being generated by the instructions you defined