Invertible Neural Networks for Inverse Problems
S. Neumayer
SIAM Conference on Imaging Science (IS'22), Virtual, March 21-25, 2022, MS53, Data-Driven Methods in Inverse Problems & Imaging - Part III of III.
In this talk, I will discuss invertible neural networks, which can be used for modelling inverse problems. If properly trained, such networks provide a way for efficiently sampling from the posterior. Starting from the theoretical analysis of the related optimization problem, we will discuss some practical implications of the established results based on numerical examples. At the end, I will outline some open issues.
@INPROCEEDINGS(http://bigwww.epfl.ch/publications/neumayer2201.html,
AUTHOR="Neumayer, S.",
TITLE="Invertible Neural Networks for Inverse Problems",
BOOKTITLE="{SIAM} Conference on Imaging Science ({IS'22})",
YEAR="2022",
editor="",
volume="",
series="",
pages="",
address="Virtual",
month="March 21-25,",
organization="",
publisher="",
note="MS53")
© 2022 SIAM. Personal use of this material is permitted. However, permission to
reprint/republish this material for advertising or promotional purposes or for creating
new collective works for resale or redistribution to servers or lists, or to reuse any
copyrighted component of this work in other works must be obtained from SIAM.
This material is presented to ensure timely dissemination of scholarly and technical work.
Copyright and all rights therein are retained by authors or by other copyright holders.
All persons copying this information are expected to adhere to the terms and constraints
invoked by each author's copyright. In most cases, these works may not be reposted without
the explicit permission of the copyright holder.