Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel
Paul Hagemann, Johannes Hertrich, Fabian Altekrüger, Robert Beinert, Jannis Chemseddine, Gabriele Steidl
Abstract
We propose conditional flows of the maximum mean discrepancy (MMD) with the negative distance kernel for posterior sampling and conditional generative modelling. This MMD, which is also known as energy distance, has several advantageous properties like efficient computation via slicing and sorting. We approximate the joint distribution of the ground truth and the observations using discrete Wasserstein gradient flows and establish an error bound for the posterior distributions. Further, we prove that our particle flow is indeed a Wasserstein gradient flow of an appropriate functional. The power of our method is demonstrated by numerical examples including conditional image generation and inverse problems like superresolution, inpainting and computed tomography in low-dose and limited-angle settings.
BibTeX
@inproceedings{
hagemann2024posterior,
title={Posterior Sampling Based on Gradient Flows of the {MMD} with Negative Distance Kernel},
author={Paul Hagemann and Johannes Hertrich and Fabian Altekr{\"u}ger and Robert Beinert and Jannis Chemseddine and Gabriele Steidl},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=YrXHEb2qMb}
}