eprintid: 10194632
rev_number: 6
eprint_status: archive
userid: 699
dir: disk0/10/19/46/32
datestamp: 2024-07-16 07:57:28
lastmod: 2024-07-16 07:57:28
status_changed: 2024-07-16 07:57:28
type: proceedings_section
metadata_visibility: show
sword_depositor: 699
creators_name: Hagemann, Paul
creators_name: Hertrich, Johannes
creators_name: Altekrüger, Fabian
creators_name: Beinert, Robert
creators_name: Chemseddine, Jannis
creators_name: Steidl, Gabriele
title: Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel
ispublished: pub
divisions: UCL
divisions: B04
divisions: F48
keywords: Bayesian inverse Problems, MMD, Gradient Flows, Deep Learning
note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
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.
date: 2024-04-08
date_type: published
publisher: ICLR
official_url: https://openreview.net/forum?id=YrXHEb2qMb
oa_status: green
full_text_type: other
language: eng
primo: open
primo_central: open_green
verified: verified_manual
elements_id: 2297228
lyricists_name: Hertrich, Johannes
lyricists_id: JHERT98
actors_name: Hertrich, Johannes
actors_id: JHERT98
actors_role: owner
full_text_status: public
pres_type: paper
series: International Conference on Learning Representations
place_of_pub: Vienna, Austria
event_title: The Twelfth International Conference on Learning Representations
event_location: Vienna
event_dates: 7 Jan 2024 - 11 Jul 2024
book_title: Proceedings of the Twelfth International Conference on Learning Representations : ICLR 2024
citation:        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   
 
document_url: https://discovery.ucl.ac.uk/id/eprint/10194632/1/posterior.pdf