Score-Based Variational Inference for Inverse Problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xue, Zhipeng, Cai, Penghao, Yuan, Xiaojun, Gao, Xiqi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909340253814784
author Xue, Zhipeng
Cai, Penghao
Yuan, Xiaojun
Gao, Xiqi
author_facet Xue, Zhipeng
Cai, Penghao
Yuan, Xiaojun
Gao, Xiqi
contents Existing diffusion-based methods for inverse problems sample from the posterior using score functions and accept the generated random samples as solutions. In applications that posterior mean is preferred, we have to generate multiple samples from the posterior which is time-consuming. In this work, by analyzing the probability density evolution of the conditional reverse diffusion process, we prove that the posterior mean can be achieved by tracking the mean of each reverse diffusion step. Based on that, we establish a framework termed reverse mean propagation (RMP) that targets the posterior mean directly. We show that RMP can be implemented by solving a variational inference problem, which can be further decomposed as minimizing a reverse KL divergence at each reverse step. We further develop an algorithm that optimizes the reverse KL divergence with natural gradient descent using score functions and propagates the mean at each reverse step. Experiments demonstrate the validity of the theory of our framework and show that our algorithm outperforms state-of-the-art algorithms on reconstruction performance with lower computational complexity in various inverse problems.
format Preprint
id arxiv_https___arxiv_org_abs_2410_05646
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Score-Based Variational Inference for Inverse Problems
Xue, Zhipeng
Cai, Penghao
Yuan, Xiaojun
Gao, Xiqi
Machine Learning
Artificial Intelligence
Information Theory
Existing diffusion-based methods for inverse problems sample from the posterior using score functions and accept the generated random samples as solutions. In applications that posterior mean is preferred, we have to generate multiple samples from the posterior which is time-consuming. In this work, by analyzing the probability density evolution of the conditional reverse diffusion process, we prove that the posterior mean can be achieved by tracking the mean of each reverse diffusion step. Based on that, we establish a framework termed reverse mean propagation (RMP) that targets the posterior mean directly. We show that RMP can be implemented by solving a variational inference problem, which can be further decomposed as minimizing a reverse KL divergence at each reverse step. We further develop an algorithm that optimizes the reverse KL divergence with natural gradient descent using score functions and propagates the mean at each reverse step. Experiments demonstrate the validity of the theory of our framework and show that our algorithm outperforms state-of-the-art algorithms on reconstruction performance with lower computational complexity in various inverse problems.
title Score-Based Variational Inference for Inverse Problems
topic Machine Learning
Artificial Intelligence
Information Theory
url https://arxiv.org/abs/2410.05646