2020/06/20 by Junqi Tang, Mike E. Davies, Mike Davies +2 · 1 citation
Computer Science · Engineering · Mathematics · #Algorithm #Artificial intelligence #Artificial neural network #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Convergence (economics) #FOS: Computer and information sciences #FOS: Mathematics #Gradient descent #Image (mathematics) #Inverse #Inverse problem #Mathematical optimization #Mathematics #Numerical methods in inverse problems #Optimization and Control (math.OC) #Point (geometry) #Sparse and Compressive Sensing Techniques #Stochastic Gradient Optimization Techniques #Stochastic gradient descent #Stochastic optimization #cs.CV #math.OC
paper · pdf · doi:10.48550/arxiv.2006.11630
openalex publication_date 2020/06/20 · arxiv created 2020/06/23 · arxiv updated 2020/06/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this work we propose an efficient stochastic plug-and-play (PnP) algorithm for imaging inverse problems. The PnP stochastic gradient descent methods have been recently proposed and shown improved performance in some imaging applications over standard deterministic PnP methods. However, current stochastic PnP methods need to frequently compute the image denoisers which can be computationally expensive. To overcome this limitation, we propose a new stochastic PnP-ADMM method which is based on introducing stochastic gradient descent inner-loops within an inexact ADMM framework. We provide the theoretical guarantee on the fixed-point convergence for our algorithm under standard assumptions. Our numerical results demonstrate the effectiveness of our approach compared with state-of-the-art PnP methods.