What's in a Prior? Learned Proximal Networks for Inverse Problems
Primary Area: representation learning for computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Inverse problems, Proximal operators, Plug-and-play, Explicit regularizer, Convergent PnP, Input convex neural networks
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
Abstract: Proximal operators are ubiquitous in inverse problems, commonly appearing as part of algorithmic strategies to regularize problems that are otherwise ill-posed. Modern deep learning models have been brought to bear for these tasks too, as in the framework of plug-and-play or deep unrolling, where they loosely resemble proximal operators. Yet, these do not provide any guarantee that these general functions, implemented by neural networks, provide a proximal operator of some function, nor do they provide any characterization of the function of which they provide some approximate proximal. Herein we provide a framework to develop learned proximal networks (LPN), which provide exact proximal operators for a data-driven regularizer, and show how a new training strategy, dubbed proximal matching, guarantees that the obtained regularizer recovers the log-prior of the true data distribution. Thus, such LPN provide general, unsupervised, proximal operators that can be used for general inverse problems. We illustrate our results in a series of cases of increasing complexity. demonstrating that these models not only result in state-of-the-art restoration results, but provide a window into the resulting priors learned from data.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
Supplementary Material: zip
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 2577