TRUMPETS: Injective Flows for Inference and Inverse Problems

Konik Kothari, Amir Ehsan Khorashadizadeh, Maarten de Hoop, Ivan Dokmanić

Research output: Contribution to conferencePaperpeer-review

Abstract

We propose injective generative models called TRUMPETs that generalize invertible normalizing flows. The proposed generators progressively increase dimension from a low-dimensional latent space. We demonstrate that TRUMPETs can be trained orders of magnitudes faster than standard flows while yielding samples of comparable or better quality. They retain many of the advantages of the standard flows such as training based on maximum likelihood and a fast, exact inverse of the generator. Since TRUMPETs are injective and have fast inverses, they can be effectively used for downstream Bayesian inference. To wit, we use TRUMPET priors for maximum a posteriori estimation in the context of image reconstruction from compressive measurements, outperforming competitive baselines in terms of reconstruction quality and speed. We then propose an efficient method for posterior characterization and uncertainty quantification with TRUMPETs by taking advantage of the low-dimensional latent space.

Original languageEnglish (US)
Pages1269-1278
Number of pages10
StatePublished - 2021
Event37th Conference on Uncertainty in Artificial Intelligence, UAI 2021 - Virtual, Online
Duration: Jul 27 2021Jul 30 2021

Conference

Conference37th Conference on Uncertainty in Artificial Intelligence, UAI 2021
CityVirtual, Online
Period7/27/217/30/21

ASJC Scopus subject areas

  • Artificial Intelligence
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'TRUMPETS: Injective Flows for Inference and Inverse Problems'. Together they form a unique fingerprint.

Cite this