Saved in:
Bibliographic Details
Main Authors: Wang, Xiaoyu, Benning, Martin, Repetti, Audrey
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.08742
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929461789720576
author Wang, Xiaoyu
Benning, Martin
Repetti, Audrey
author_facet Wang, Xiaoyu
Benning, Martin
Repetti, Audrey
contents Unfolded proximal neural networks (PNNs) form a family of methods that combines deep learning and proximal optimization approaches. They consist in designing a neural network for a specific task by unrolling a proximal algorithm for a fixed number of iterations, where linearities can be learned from prior training procedure. PNNs have shown to be more robust than traditional deep learning approaches while reaching at least as good performances, in particular in computational imaging. However, training PNNs still depends on the efficiency of available training algorithms. In this work, we propose a lifted training formulation based on Bregman distances for unfolded PNNs. Leveraging the deterministic mini-batch block-coordinate forward-backward method, we design a bespoke computational strategy beyond traditional back-propagation methods for solving the resulting learning problem efficiently. We assess the behaviour of the proposed training approach for PNNs through numerical simulations on image denoising, considering a denoising PNN whose structure is based on dual proximal-gradient iterations.
format Preprint
id arxiv_https___arxiv_org_abs_2408_08742
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A lifted Bregman strategy for training unfolded proximal neural network Gaussian denoisers
Wang, Xiaoyu
Benning, Martin
Repetti, Audrey
Optimization and Control
Computer Vision and Pattern Recognition
65K10, 68T01
Unfolded proximal neural networks (PNNs) form a family of methods that combines deep learning and proximal optimization approaches. They consist in designing a neural network for a specific task by unrolling a proximal algorithm for a fixed number of iterations, where linearities can be learned from prior training procedure. PNNs have shown to be more robust than traditional deep learning approaches while reaching at least as good performances, in particular in computational imaging. However, training PNNs still depends on the efficiency of available training algorithms. In this work, we propose a lifted training formulation based on Bregman distances for unfolded PNNs. Leveraging the deterministic mini-batch block-coordinate forward-backward method, we design a bespoke computational strategy beyond traditional back-propagation methods for solving the resulting learning problem efficiently. We assess the behaviour of the proposed training approach for PNNs through numerical simulations on image denoising, considering a denoising PNN whose structure is based on dual proximal-gradient iterations.
title A lifted Bregman strategy for training unfolded proximal neural network Gaussian denoisers
topic Optimization and Control
Computer Vision and Pattern Recognition
65K10, 68T01
url https://arxiv.org/abs/2408.08742