Provably Convergent Algorithms for Solving Inverse Problems Using Generative Models

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 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.

arXiv commentarXiv admin note: text overlap with arXiv:1810.03587, arXiv:1802.08406

References in corpus (8)

• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Energy-based Generative Adversarial Network
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Compressed Sensing using Generative Models
• Compressed Sensing with Deep Image Prior and Learned Regularization
• Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors
• Modeling Sparse Deviations for Compressed Sensing using Generative Models
• Fast Algorithms for Demixing Sparse Signals from Nonlinear Observations