Learning optimal nonlinearities for iterative thresholding algorithms

Abstract

Iterative shrinkage/thresholding algorithm (ISTA) is a well-studied method for finding sparse solutions to ill-posed inverse problems. In this letter, we present a data-driven scheme for learning optimal thresholding functions for ISTA. The proposed scheme is obtained by relating iterations of ISTA to layers of a simple deep neural network (DNN) and developing a corresponding error backpropagation algorithm that allows to fine-tune the thresholding functions. Simulations on sparse statistical signals illustrate potential gains in estimation quality due to the proposed data adaptive ISTA.

References in corpus (5)

• Message Passing Algorithms for Compressed Sensing
• A Deep Learning Approach to Structured Signal Recovery
• $L_{1/2}$ Regularization: Convergence of Iterative Half Thresholding Algorithm
• Linear Convergence of Adaptively Iterative Thresholding Algorithms for Compressed Sensing
• Learning Efficient Structured Sparse Models

Cited by in corpus (13)

• Deep Convolutional Neural Network for Inverse Problems in Imaging
• AMP-Inspired Deep Networks for Sparse Linear Inverse Problems
• RARE: Image Reconstruction using Deep Priors Learned without Ground Truth
• Efficient and accurate inversion of multiple scattering with deep learning
• Deep BCD-Net Using Identical Encoding-Decoding CNN Structures for Iterative Image Recovery
• Dense Recurrent Neural Networks for Accelerated MRI: History-Cognizant Unrolling of Optimization Algorithms
• Learned Conjugate Gradient Descent Network for Massive MIMO Detection
• Solving Sparse Linear Inverse Problems in Communication Systems: A Deep Learning Approach With Adaptive Depth
• SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees
• CAPPA: Continuous-time Accelerated Proximal Point Algorithm for Sparse Recovery
• Learning-based Image Reconstruction via Parallel Proximal Algorithm
• Learning Convex Regularizers for Optimal Bayesian Denoising
• Frank-Wolfe Network: An Interpretable Deep Structure for Non-Sparse Coding