Beyond adaptive gradient: Fast-Controlled Minibatch Algorithm for large-scale optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Coppola, Corrado, Papa, Lorenzo, Amerini, Irene, Palagi, Laura
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929632115163136
author Coppola, Corrado
Papa, Lorenzo
Amerini, Irene
Palagi, Laura
author_facet Coppola, Corrado
Papa, Lorenzo
Amerini, Irene
Palagi, Laura
contents Adaptive gradient methods have been increasingly adopted by deep learning community due to their fast convergence and reduced sensitivity to hyper-parameters. However, these methods come with limitations, such as increased memory requirements for elements like moving averages and a poorly understood convergence theory. To overcome these challenges, we introduce F-CMA, a Fast-Controlled Mini-batch Algorithm with a random reshuffling method featuring a sufficient decrease condition and a line-search procedure to ensure loss reduction per epoch, along with its deterministic proof of global convergence to a stationary point. To evaluate the F-CMA, we integrate it into conventional training protocols for classification tasks involving both convolutional neural networks and vision transformer models, allowing for a direct comparison with popular optimizers. Computational tests show significant improvements, including a decrease in the overall training time by up to 68%, an increase in per-epoch efficiency by up to 20%, and in model accuracy by up to 5%.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15795
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Beyond adaptive gradient: Fast-Controlled Minibatch Algorithm for large-scale optimization
Coppola, Corrado
Papa, Lorenzo
Amerini, Irene
Palagi, Laura
Machine Learning
Optimization and Control
Adaptive gradient methods have been increasingly adopted by deep learning community due to their fast convergence and reduced sensitivity to hyper-parameters. However, these methods come with limitations, such as increased memory requirements for elements like moving averages and a poorly understood convergence theory. To overcome these challenges, we introduce F-CMA, a Fast-Controlled Mini-batch Algorithm with a random reshuffling method featuring a sufficient decrease condition and a line-search procedure to ensure loss reduction per epoch, along with its deterministic proof of global convergence to a stationary point. To evaluate the F-CMA, we integrate it into conventional training protocols for classification tasks involving both convolutional neural networks and vision transformer models, allowing for a direct comparison with popular optimizers. Computational tests show significant improvements, including a decrease in the overall training time by up to 68%, an increase in per-epoch efficiency by up to 20%, and in model accuracy by up to 5%.
title Beyond adaptive gradient: Fast-Controlled Minibatch Algorithm for large-scale optimization
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2411.15795