Robust Stochastically-Descending Unrolled Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hadou, Samar, NaderiAlizadeh, Navid, Ribeiro, Alejandro
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912137642770432
author Hadou, Samar
NaderiAlizadeh, Navid
Ribeiro, Alejandro
author_facet Hadou, Samar
NaderiAlizadeh, Navid
Ribeiro, Alejandro
contents Deep unrolling, or unfolding, is an emerging learning-to-optimize method that unrolls a truncated iterative algorithm in the layers of a trainable neural network. However, the convergence guarantees and generalizability of the unrolled networks are still open theoretical problems. To tackle these problems, we provide deep unrolled architectures with a stochastic descent nature by imposing descending constraints during training. The descending constraints are forced layer by layer to ensure that each unrolled layer takes, on average, a descent step toward the optimum during training. We theoretically prove that the sequence constructed by the outputs of the unrolled layers is then guaranteed to converge for unseen problems, assuming no distribution shift between training and test problems. We also show that standard unrolling is brittle to perturbations, and our imposed constraints provide the unrolled networks with robustness to additive noise and perturbations. We numerically assess unrolled architectures trained under the proposed constraints in two different applications, including the sparse coding using learnable iterative shrinkage and thresholding algorithm (LISTA) and image inpainting using proximal generative flow (GLOW-Prox), and demonstrate the performance and robustness benefits of the proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2312_15788
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Robust Stochastically-Descending Unrolled Networks
Hadou, Samar
NaderiAlizadeh, Navid
Ribeiro, Alejandro
Machine Learning
Signal Processing
Deep unrolling, or unfolding, is an emerging learning-to-optimize method that unrolls a truncated iterative algorithm in the layers of a trainable neural network. However, the convergence guarantees and generalizability of the unrolled networks are still open theoretical problems. To tackle these problems, we provide deep unrolled architectures with a stochastic descent nature by imposing descending constraints during training. The descending constraints are forced layer by layer to ensure that each unrolled layer takes, on average, a descent step toward the optimum during training. We theoretically prove that the sequence constructed by the outputs of the unrolled layers is then guaranteed to converge for unseen problems, assuming no distribution shift between training and test problems. We also show that standard unrolling is brittle to perturbations, and our imposed constraints provide the unrolled networks with robustness to additive noise and perturbations. We numerically assess unrolled architectures trained under the proposed constraints in two different applications, including the sparse coding using learnable iterative shrinkage and thresholding algorithm (LISTA) and image inpainting using proximal generative flow (GLOW-Prox), and demonstrate the performance and robustness benefits of the proposed method.
title Robust Stochastically-Descending Unrolled Networks
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2312.15788