Async-RED: A Provably Convergent Asynchronous Block Parallel Stochastic Method using Deep Denoising PriorsDownload PDF

28 Sept 2020, 15:48 (modified: 11 Feb 2021, 03:03)ICLR 2021 SpotlightReaders: Everyone
Keywords: Regularization by denoising, Computational imaging, asynchronous parallel algorithm, Deep denoising priors
Abstract: Regularization by denoising (RED) is a recently developed framework for solving inverse problems by integrating advanced denoisers as image priors. Recent work has shown its state-of-the-art performance when combined with pre-trained deep denoisers. However, current RED algorithms are inadequate for parallel processing on multicore systems. We address this issue by proposing a new{asynchronous RED (Async-RED) algorithm that enables asynchronous parallel processing of data, making it significantly faster than its serial counterparts for large-scale inverse problems. The computational complexity of Async-RED is further reduced by using a random subset of measurements at every iteration. We present a complete theoretical analysis of the algorithm by establishing its convergence under explicit assumptions on the data-fidelity and the denoiser. We validate Async-RED on image recovery using pre-trained deep denoisers as priors.
One-sentence Summary: Our work develops a novel deep-regularized asynchronous parallel method with provable convergence guarantees for solving large-scale inverse problems.
Supplementary Material: zip
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
11 Replies