AutoSGD: Automatic Learning Rate Selection for Stochastic Gradient Descent

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Surjanovic, Nikola, Bouchard-Côté, Alexandre, Campbell, Trevor
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908381924556800
author Surjanovic, Nikola
Bouchard-Côté, Alexandre
Campbell, Trevor
author_facet Surjanovic, Nikola
Bouchard-Côté, Alexandre
Campbell, Trevor
contents The learning rate is an important tuning parameter for stochastic gradient descent (SGD) and can greatly influence its performance. However, appropriate selection of a learning rate schedule across all iterations typically requires a non-trivial amount of user tuning effort. To address this, we introduce AutoSGD: an SGD method that automatically determines whether to increase or decrease the learning rate at a given iteration and then takes appropriate action. We introduce theory supporting the convergence of AutoSGD, along with its deterministic counterpart for standard gradient descent. Empirical results suggest strong performance of the method on a variety of traditional optimization problems and machine learning tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21651
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AutoSGD: Automatic Learning Rate Selection for Stochastic Gradient Descent
Surjanovic, Nikola
Bouchard-Côté, Alexandre
Campbell, Trevor
Machine Learning
Optimization and Control
Computation
The learning rate is an important tuning parameter for stochastic gradient descent (SGD) and can greatly influence its performance. However, appropriate selection of a learning rate schedule across all iterations typically requires a non-trivial amount of user tuning effort. To address this, we introduce AutoSGD: an SGD method that automatically determines whether to increase or decrease the learning rate at a given iteration and then takes appropriate action. We introduce theory supporting the convergence of AutoSGD, along with its deterministic counterpart for standard gradient descent. Empirical results suggest strong performance of the method on a variety of traditional optimization problems and machine learning tasks.
title AutoSGD: Automatic Learning Rate Selection for Stochastic Gradient Descent
topic Machine Learning
Optimization and Control
Computation
url https://arxiv.org/abs/2505.21651