Metadata only
Date
2023-01Type
- Report
ETH Bibliography
yes
Altmetrics
Abstract
A large class of inverse problems for PDEs are only well-defined as mappings from operators to functions. Existing operator learning frameworks map functions to functions and need to be modified to learn inverse maps from data. We propose a novel architecture termed Neural Inverse Operators (NIOs) to solve these PDE inverse problems. Motivated by the underlying mathematical structure, NIO is based on a suitable composition of DeepONets and FNOs to approximate mappings from operators to functions. A variety of experiments are presented to demonstrate that NIOs significantly outperform baselines and solve PDE inverse problems robustly, accurately and are several orders of magnitude faster than existing direct and PDE-constrained optimization methods. Show more
Publication status
publishedExternal links
Journal / series
SAM Research ReportVolume
Publisher
Seminar for Applied Mathematics, ETH ZurichOrganisational unit
03851 - Mishra, Siddhartha / Mishra, Siddhartha
02889 - ETH Institut für Theoretische Studien / ETH Institute for Theoretical Studies
Related publications and datasets
Is previous version of: http://hdl.handle.net/20.500.11850/656484
More
Show all metadata
ETH Bibliography
yes
Altmetrics