Proximal Residual Flows for Bayesian Inverse Problems

Abstract

Normalizing flows are a powerful tool for generative modelling, density estimation and posterior reconstruction in Bayesian inverse problems. In this paper, we introduce proximal residual flows, a new architecture of normalizing flows. Based on the fact, that proximal neural networks are by definition averaged operators, we ensure invertibility of certain residual blocks. Moreover, we extend the architecture to conditional proximal residual flows for posterior reconstruction within Bayesian inverse problems. We demonstrate the performance of proximal residual flows on numerical examples.

References in corpus (7)

• Inertial Proximal Alternating Linearized Minimization (iPALM) for Nonconvex and Nonsmooth Problems
• Convolutional Proximal Neural Networks and Plug-and-Play Algorithms
• Parseval Proximal Neural Networks
• Stabilizing Invertible Neural Networks Using Mixture Models
• Stochastic Normalizing Flows for Inverse Problems: a Markov Chains Viewpoint
• Inertial Stochastic PALM (iSPALM) and Applications in Machine Learning
• WPPNets and WPPFlows: The Power of Wasserstein Patch Priors for Superresolution