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

by   Yu Sun, et al.

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 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.


page 8

page 23

page 24

page 25


Joint Reconstruction and Calibration using Regularization by Denoising

Regularization by denoising (RED) is a broadly applicable framework for ...

Block Coordinate Regularization by Denoising

We consider the problem of estimating a vector from its noisy measuremen...

Acceleration of RED via Vector Extrapolation

Models play an important role in inverse problems, serving as the prior ...

Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Condition

The plug-and-play priors (PnP) and regularization by denoising (RED) met...

Bregman Plug-and-Play Priors

The past few years have seen a surge of activity around integration of d...

Scalable Plug-and-Play ADMM with Convergence Guarantees

Plug-and-play priors (PnP) is a broadly applicable methodology for solvi...

A Projectional Ansatz to Reconstruction

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