DeepGEM: Generalized Expectation-Maximization for Blind Inversion
Abstract
Typically, inversion algorithms assume that a forward model, which relates a source to its resulting measurements, is known and fixed. Using collected indirect measurements and the forward model, the goal becomes to recover the source. When the forward model is unknown, or imperfect, artifacts due to model mismatch occur in the recovery of the source. In this paper, we study the problem of blind inversion: solving an inverse problem with unknown or imperfect knowledge of the forward model parameters. We propose DeepGEM, a variational Expectation-Maximization (EM) framework that can be used to solve for the unknown parameters of the forward model in an unsupervised manner. DeepGEM makes use of a normalizing flow generative network to efficiently capture complex posterior distributions, which leads to more accurate evaluation of the source's posterior distribution used in EM. We showcase the effectiveness of our DeepGEM approach by achieving strong performance on the challenging problem of blind seismic tomography, where we significantly outperform the standard method used in seismology. We also demonstrate the generality of DeepGEM by applying it to a simple case of blind deconvolution.
Additional Information
This research was carried out at the Jet Propulsion Laboratory and the California Institute of Technology under a contract with the National Aeronautics and Space Administration and funded through the President's and Director's Research and Development Fund (PDRDF). This work was sponsored by Beyond Limits, Jet Propulsion Laboratory Award 1669417, NSF Award 2048237, and generous gifts from Luke Wang and Yi Li. Additionally, we would like to thank He Sun for many helpful discussions. We declare no competing interests.Attached Files
Published - GAO_ANIPS_2021.pdf
Files
Name | Size | Download all |
---|---|---|
md5:84651ebf9993cdc597fc3f339a9c5b5b
|
1.2 MB | Preview Download |
Additional details
- Eprint ID
- 117607
- Resolver ID
- CaltechAUTHORS:20221026-200931912
- NASA/JPL/Caltech
- JPL President and Director's Fund
- Beyond Limits
- JPL
- 1669417
- NSF
- CCF-2048237
- Created
-
2022-10-26Created from EPrint's datestamp field
- Updated
-
2022-10-26Created from EPrint's last_modified field
- Caltech groups
- Seismological Laboratory, Astronomy Department, Center for Geomechanics and Mitigation of Geohazards (GMG), Division of Geological and Planetary Sciences, Center for Autonomous Systems and Technologies (CAST)