Log In Sign Up

Provably Convergent Algorithms for Solving Inverse Problems Using Generative Models

by   Rakib Hyder, et al.

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 deep generative networks). 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.


page 3

page 15

page 16

page 17


Algorithmic Aspects of Inverse Problems Using Generative Models

The traditional approach of hand-crafting priors (such as sparsity) for ...

Solving Inverse Problems for Spectral Energy Distributions with Deep Generative Networks

We propose an end-to-end approach for solving inverse problems for a cla...

Solving Bilinear Inverse Problems using Deep Generative Priors

This paper proposes a new framework to handle the bilinear inverse probl...

Benchmarking Invertible Architectures on Inverse Problems

Recent work demonstrated that flow-based invertible neural networks are ...

Understanding and mitigating exploding inverses in invertible neural networks

Invertible neural networks (INNs) have been used to design generative mo...

Solving Inverse Problems by Joint Posterior Maximization with a VAE Prior

In this paper we address the problem of solving ill-posed inverse proble...

A Projectional Ansatz to Reconstruction

Recently the field of inverse problems has seen a growing usage of mathe...