UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel

Hagemann, Paul; Hertrich, Johannes; Altekrüger, Fabian; Beinert, Robert; Chemseddine, Jannis; Steidl, Gabriele; (2024) Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel. In: Proceedings of the Twelfth International Conference on Learning Representations : ICLR 2024. ICLR: Vienna, Austria. Green open access

[thumbnail of posterior.pdf]
Preview
PDF
posterior.pdf - Published Version

Download (15MB) | Preview

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.

Type: Proceedings paper
Title: Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel
Event: The Twelfth International Conference on Learning Representations
Location: Vienna
Dates: 7 Jan 2024 - 11 Jul 2024
Open access status: An open access version is available from UCL Discovery
Publisher version: https://openreview.net/forum?id=YrXHEb2qMb
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Bayesian inverse Problems, MMD, Gradient Flows, Deep Learning
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10194632
Downloads since deposit
Loading...
13Downloads
Download activity - last month
Loading...
Download activity - last 12 months
Loading...
Downloads by country - last 12 months
Loading...

Archive Staff Only

View Item View Item