Algorithms for solving inverse problems using generative models

Date
2019-01-01
Authors
Shah, Viraj
Journal Title
Journal ISSN
Volume Title
Publisher
Source URI
Altmetrics
Authors
Research Projects
Organizational Units
Journal Issue
Series
Abstract

The traditional approach of hand-crafting priors (such as sparsity) for solving inverse problems is slowly being replaced by the use of richer learned priors (such as those modeled by generative adversarial networks, or GANs). In this work, we study the algorithmic aspects of such a learning-based approach from a theoretical perspective. For certain generative network architectures, we establish a simple non-convex algorithmic approach that (a) theoretically enjoys linear convergence guarantees for certain linear and nonlinear inverse problems, and (b) empirically improves upon conventional techniques such as back-propagation. We support our claims with the experimental results for solving various inverse problems. We also propose an extension of our approach that can handle model mismatch (i.e., situations where the generative network prior is not exactly applicable.) Together, our contributions serve as building blocks towards a principled use of generative models in inverse problems with more complete algorithmic understanding.

Description
Keywords
Compressive Sensing, Generative Models, Inverse Problems, Signal Processing
Citation