Poster

Composing Normalizing Flows for Inverse Problems

Jay Whang · Erik Lindgren · Alexandros Dimakis

Keywords: [ Sparsity and Compressed Sensing ] [ Algorithms ]

[ Abstract ]
[ Paper ]
[ Visit Poster at Spot C0 in Virtual World ]
Wed 21 Jul 9 a.m. PDT — 11 a.m. PDT
 
Spotlight presentation: Probabilistic Methods 1
Wed 21 Jul 5 a.m. PDT — 6 a.m. PDT

Abstract:

Given an inverse problem with a normalizing flow prior, we wish to estimate the distribution of the underlying signal conditioned on the observations. We approach this problem as a task of conditional inference on the pre-trained unconditional flow model. We first establish that this is computationally hard for a large class of flow models. Motivated by this, we propose a framework for approximate inference that estimates the target conditional as a composition of two flow models. This formulation leads to a stable variational inference training procedure that avoids adversarial training. Our method is evaluated on a variety of inverse problems and is shown to produce high-quality samples with uncertainty quantification. We further demonstrate that our approach can be amortized for zero-shot inference.

Chat is not available.