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

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.

[1]  Lei Zhang,et al.  Deep Plug-And-Play Super-Resolution for Arbitrary Blur Kernels , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[3]  Stanley H. Chan,et al.  Plug-and-Play ADMM for Image Restoration: Fixed-Point Convergence and Applications , 2016, IEEE Transactions on Computational Imaging.

[4]  Richard G. Baraniuk,et al.  From Denoising to Compressed Sensing , 2014, IEEE Transactions on Information Theory.

[5]  Bálint Antal,et al.  Image Data Resource: a bioimage data integration and publication platform , 2017, Nature Methods.

[6]  Wotao Yin,et al.  A2BCD: Asynchronous Acceleration with Optimal Complexity , 2018, ICLR.

[7]  Charles A. Bouman,et al.  Plug-and-Play Methods for Magnetic Resonance Imaging: Using Denoisers for Image Recovery , 2019, IEEE Signal Processing Magazine.

[8]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

[9]  Yuichi Yoshida,et al.  Spectral Normalization for Generative Adversarial Networks , 2018, ICLR.

[10]  Yu Sun,et al.  Block Coordinate Regularization by Denoising , 2019, IEEE Transactions on Computational Imaging.

[11]  Tuo Zhao,et al.  Towards Understanding Acceleration Tradeoff between Momentum and Asynchrony in Nonconvex Stochastic Optimization , 2018, NeurIPS.

[12]  Sundeep Rangan,et al.  Inference for Generalized Linear Models via Alternating Directions and Bethe Free Energy Minimization , 2015, IEEE Transactions on Information Theory.

[13]  Cem Anil,et al.  Sorting out Lipschitz function approximation , 2018, ICML.

[14]  Michael Elad,et al.  Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries , 2006, IEEE Transactions on Image Processing.

[15]  Yurii Nesterov,et al.  Efficiency of Coordinate Descent Methods on Huge-Scale Optimization Problems , 2012, SIAM J. Optim..

[16]  Philip M. Long,et al.  The Singular Values of Convolutional Layers , 2018, ICLR.

[17]  Robert D. Nowak,et al.  Wavelet-based image estimation: an empirical Bayes approach using Jeffrey's noninformative prior , 2001, IEEE Trans. Image Process..

[18]  Brendt Wohlberg,et al.  An Online Plug-and-Play Algorithm for Regularized Image Reconstruction , 2018, IEEE Transactions on Computational Imaging.

[19]  Richard G. Baraniuk,et al.  BM3D-PRGAMP: Compressive phase retrieval based on BM3D denoising , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[20]  Ming Yan,et al.  ARock: an Algorithmic Framework for Asynchronous Parallel Coordinate Updates , 2015, SIAM J. Sci. Comput..

[21]  Saeed Ghadimi,et al.  Accelerated gradient methods for nonconvex nonlinear and stochastic programming , 2013, Math. Program..

[22]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[23]  Sundeep Rangan,et al.  Plug in estimation in high dimensional linear inverse problems a rigorous analysis , 2018, NeurIPS.

[24]  Brendt Wohlberg,et al.  Provable Convergence of Plug-and-Play Priors With MMSE Denoisers , 2020, IEEE Signal Processing Letters.

[25]  Raja Giryes,et al.  Image Restoration by Iterative Denoising and Backward Projections , 2017, IEEE Transactions on Image Processing.

[26]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[27]  Wei Zhang,et al.  Asynchronous Decentralized Parallel Stochastic Gradient Descent , 2017, ICML.

[28]  Li Fei-Fei,et al.  Distributed Asynchronous Optimization with Unbounded Delays: How Slow Can You Go? , 2018, ICML.

[29]  Brendt Wohlberg,et al.  Plug-and-Play priors for model based reconstruction , 2013, 2013 IEEE Global Conference on Signal and Information Processing.

[30]  Stephen J. Wright Coordinate descent algorithms , 2015, Mathematical Programming.

[31]  Wotao Yin,et al.  On Unbounded Delays in Asynchronous Parallel Fixed-Point Algorithms , 2016, J. Sci. Comput..

[32]  Xiaohan Chen,et al.  Plug-and-Play Methods Provably Converge with Properly Trained Denoisers , 2019, ICML.

[33]  Mário A. T. Figueiredo,et al.  Wavelet-Based Image Estimation : An Empirical Bayes Approach Using Jeffreys ’ Noninformative Prior , 2001 .

[34]  José M. Bioucas-Dias,et al.  A Convergent Image Fusion Algorithm Using Scene-Adapted Gaussian-Mixture-Based Denoising , 2019, IEEE Transactions on Image Processing.

[35]  Wangmeng Zuo,et al.  Learning Deep CNN Denoiser Prior for Image Restoration , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Ying Fu,et al.  Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems , 2020, ICML.

[37]  Mathews Jacob,et al.  A Fast Majorize–Minimize Algorithm for the Recovery of Sparse and Low-Rank Matrices , 2012, IEEE Transactions on Image Processing.

[38]  Lei Tian,et al.  Regularized Fourier Ptychography Using an Online Plug-and-play Algorithm , 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[39]  Alexander Shapiro,et al.  Stochastic Approximation approach to Stochastic Programming , 2013 .

[40]  Robert D. Nowak,et al.  An EM algorithm for wavelet-based image restoration , 2003, IEEE Trans. Image Process..

[41]  Jiaming Liu,et al.  SIMBA: Scalable Inversion in Optical Tomography Using Deep Denoising Priors , 2019, IEEE Journal of Selected Topics in Signal Processing.

[42]  Charles A. Bouman,et al.  Plug-and-Play Unplugged: Optimization Free Reconstruction using Consensus Equilibrium , 2017, SIAM J. Imaging Sci..

[43]  Ohad Shamir,et al.  Optimal Distributed Online Prediction Using Mini-Batches , 2010, J. Mach. Learn. Res..

[44]  Charles A. Bouman,et al.  Plug-and-Play Priors for Bright Field Electron Tomography and Sparse Interpolation , 2015, IEEE Transactions on Computational Imaging.

[45]  Michael Elad,et al.  Regularization by Denoising via Fixed-Point Projection (RED-PRO) , 2020, SIAM J. Imaging Sci..

[46]  Michael Elad,et al.  The Little Engine That Could: Regularization by Denoising (RED) , 2016, SIAM J. Imaging Sci..

[47]  Yurii Nesterov,et al.  Introductory Lectures on Convex Optimization - A Basic Course , 2014, Applied Optimization.

[48]  Yijun Huang,et al.  Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization , 2015, NIPS.

[49]  Ming Yan,et al.  On the Convergence of Asynchronous Parallel Iteration with Unbounded Delays , 2016, Journal of the Operations Research Society of China.

[50]  Philip Schniter,et al.  Regularization by Denoising: Clarifications and New Interpretations , 2018, IEEE Transactions on Computational Imaging.

[51]  Stephen J. Wright,et al.  Hogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent , 2011, NIPS.

[52]  Stephen J. Wright,et al.  Asynchronous Stochastic Coordinate Descent: Parallelism and Convergence Properties , 2014, SIAM J. Optim..

[53]  Matthias Zwicker,et al.  Deep Mean-Shift Priors for Image Restoration , 2017, NIPS.

[54]  Michael Elad,et al.  DeepRED: Deep Image Prior Powered by RED , 2019, ICCV 2019.

[55]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[56]  Stephen P. Boyd,et al.  A Primer on Monotone Operator Methods , 2015 .

[57]  Wotao Yin,et al.  Asynchronous Coordinate Descent under More Realistic Assumptions , 2017, NIPS.

[58]  Stephen J. Wright,et al.  An asynchronous parallel stochastic coordinate descent algorithm , 2013, J. Mach. Learn. Res..

[59]  Amir Beck,et al.  On the Convergence of Block Coordinate Descent Type Methods , 2013, SIAM J. Optim..

[60]  Michael Möller,et al.  Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[61]  Richard G. Baraniuk,et al.  prDeep: Robust Phase Retrieval with a Flexible Deep Network , 2018, ICML.