A Variational Inequality Model for Learning Neural Networks

Neural networks have become ubiquitous tools for solving signal and image processing problems, and they often outperform standard approaches. Nevertheless, training the layers of a neural network is a challenging task in many applications. The prevalent training procedure consists of minimizing high...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 1 - 5
Main Authors: Combettes, Patrick L., Pesquet, Jean-Christophe, Repetti, Audrey
Format: Conference Proceeding
Language:English
Published: IEEE 04.06.2023
Subjects:
Block-iterative algorithm
MRI
Neural networks
Numerical models
Signal processing
Signal processing algorithms
Task analysis
Training
Transfer learning
variational inequality
ISSN:2379-190X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neural networks have become ubiquitous tools for solving signal and image processing problems, and they often outperform standard approaches. Nevertheless, training the layers of a neural network is a challenging task in many applications. The prevalent training procedure consists of minimizing highly non-convex objectives based on data sets of huge dimension. In this context, current methodologies are not guaranteed to produce global solutions. We present an alternative approach which foregoes the optimization framework and adopts a variational inequality formalism. The associated algorithm guarantees convergence of the iterates to a true solution of the variational inequality and it possesses an efficient block-iterative structure. A numerical application is presented.
ISSN:2379-190X
DOI:10.1109/ICASSP49357.2023.10095688