Scalable Plug-and-Play ADMM with Convergence Guarantees

Abstract

Plug-and-play priors (PnP) is a broadly applicable methodology for solving inverse problems by exploiting statistical priors specified as denoisers. Recent work has reported the state-of-the-art performance of PnP algorithms using pre-trained deep neural nets as denoisers in a number of imaging applications. However, current PnP algorithms are impractical in large-scale settings due to their heavy computational and memory requirements. This work addresses this issue by proposing an incremental variant of the widely used PnP-ADMM algorithm, making it scalable to large-scale datasets. We theoretically analyze the convergence of the algorithm under a set of explicit assumptions, extending recent theoretical results in the area. Additionally, we show the effectiveness of our algorithm with nonsmooth data-fidelity terms and deep neural net priors, its fast convergence compared to existing PnP algorithms, and its scalability in terms of speed and memory.

arXiv commentFirst three authors contribute equally and are listed in alphabetical order

References in corpus (17)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• Spectral Normalization for Generative Adversarial Networks
• Fast Image Recovery Using Variable Splitting and Constrained Optimization
• Denoising Prior Driven Deep Neural Network for Image Restoration
• Plug and play methods for magnetic resonance imaging (long version)
• CAT2000: A Large Scale Fixation Dataset for Boosting Saliency Research
• An Online Plug-and-Play Algorithm for Regularized Image Reconstruction
• The Singular Values of Convolutional Layers
• High-throughput intensity diffraction tomography with a computational microscope
• Plug-and-Play Methods Provably Converge with Properly Trained Denoisers
• Compressive Imaging via Approximate Message Passing with Image Denoising
• Deep Mean-Shift Priors for Image Restoration
• Plug-in Estimation in High-Dimensional Linear Inverse Problems: A Rigorous Analysis
• Fast Stochastic Alternating Direction Method of Multipliers
• Faster Stochastic Alternating Direction Method of Multipliers for Nonconvex Optimization
• Deep Learning Techniques for Inverse Problems in Imaging

Cited by in corpus (3)

• Learning to Optimize: A Primer and A Benchmark
• TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems
• Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems