Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published July 2021 | Supplemental Material + Submitted + Published
Journal Article Open

Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference

Abstract

We propose a Multiscale Invertible Generative Network (MsIGN) and associated training algorithm that leverages multiscale structure to solve high-dimensional Bayesian inference. To address the curse of dimensionality, MsIGN exploits the low-dimensional nature of the posterior, and generates samples from coarse to fine scale (low to high dimension) by iteratively upsampling and refining samples. MsIGN is trained in a multi-stage manner to minimize the Jeffreys divergence, which avoids mode dropping in high-dimensional cases. On two high-dimensional Bayesian inverse problems, we show superior performance of MsIGN over previous approaches in posterior approximation and multiple mode capture. On the natural image synthesis task, MsIGN achieves superior performance in bits-per-dimension over baseline models and yields great interpret-ability of its neurons in intermediate layers.

Additional Information

© 2021 by the author(s). We appreciate valuable comments and discussion from the reviewers. The work of Thomas Y. Hou was in part supported by NSF Grants DMS-1912654 and DMS-1907977, and Shumao Zhang was in part supported by NSF Grant DMS-1912654. The authors would also like to thank Ka Chun Lam and Xiaodong He for their helpful discussion and thank Lin Xiao, Qiang Liu and Bo Dai for their helpful suggestions.

Attached Files

Published - zhang21z.pdf

Submitted - 2105.05489.pdf

Supplemental Material - zhang21z-supp.pdf

Files

zhang21z-supp.pdf
Files (38.8 MB)
Name Size Download all
md5:cb678db327773eba9da68132a4cdf3ee
22.1 MB Preview Download
md5:ad2f78cd99447909a61ea6b1f2413a97
6.5 MB Preview Download
md5:9089a361ce35d95957f9970f7790be7b
10.2 MB Preview Download

Additional details

Created:
August 20, 2023
Modified:
October 24, 2023