Saved in:
Bibliographic Details
Main Authors: Ebrahimi, Zeinab, Batista, Gustavo, Deghat, Mohammad
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.03619
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910290030886912
author Ebrahimi, Zeinab
Batista, Gustavo
Deghat, Mohammad
author_facet Ebrahimi, Zeinab
Batista, Gustavo
Deghat, Mohammad
contents Stochastic gradient descent (SGD) and its many variants are the widespread optimization algorithms for training deep neural networks. However, SGD suffers from inevitable drawbacks, including vanishing gradients, lack of theoretical guarantees, and substantial sensitivity to input. The Alternating Direction Method of Multipliers (ADMM) has been proposed to address these shortcomings as an effective alternative to the gradient-based methods. It has been successfully employed for training deep neural networks. However, ADMM-based optimizers have a slow convergence rate. This paper proposes an Anderson Acceleration for Deep Learning ADMM (AA-DLADMM) algorithm to tackle this drawback. The main intention of the AA-DLADMM algorithm is to employ Anderson acceleration to ADMM by considering it as a fixed-point iteration and attaining a nearly quadratic convergence rate. We verify the effectiveness and efficiency of the proposed AA-DLADMM algorithm by conducting extensive experiments on four benchmark datasets contrary to other state-of-the-art optimizers.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03619
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AA-DLADMM: An Accelerated ADMM-based Framework for Training Deep Neural Networks
Ebrahimi, Zeinab
Batista, Gustavo
Deghat, Mohammad
Machine Learning
Systems and Control
Stochastic gradient descent (SGD) and its many variants are the widespread optimization algorithms for training deep neural networks. However, SGD suffers from inevitable drawbacks, including vanishing gradients, lack of theoretical guarantees, and substantial sensitivity to input. The Alternating Direction Method of Multipliers (ADMM) has been proposed to address these shortcomings as an effective alternative to the gradient-based methods. It has been successfully employed for training deep neural networks. However, ADMM-based optimizers have a slow convergence rate. This paper proposes an Anderson Acceleration for Deep Learning ADMM (AA-DLADMM) algorithm to tackle this drawback. The main intention of the AA-DLADMM algorithm is to employ Anderson acceleration to ADMM by considering it as a fixed-point iteration and attaining a nearly quadratic convergence rate. We verify the effectiveness and efficiency of the proposed AA-DLADMM algorithm by conducting extensive experiments on four benchmark datasets contrary to other state-of-the-art optimizers.
title AA-DLADMM: An Accelerated ADMM-based Framework for Training Deep Neural Networks
topic Machine Learning
Systems and Control
url https://arxiv.org/abs/2401.03619