Saved in:
Bibliographic Details
Main Author: Faraj, Nathan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.13457
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913847772708864
author Faraj, Nathan
author_facet Faraj, Nathan
contents This paper introduces a novel method for optimizing learning rates in machine learning. A previously unrecognized proportionality between learning rates and dataset sizes is discovered, providing valuable insights into how dataset scale influences training dynamics. Additionally, a cumulative learning constant is identified, offering a framework for designing and optimizing advanced learning rate schedules. These findings have the potential to enhance training efficiency and performance across a wide range of machine learning applications.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13457
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Tuning Learning Rates with the Cumulative-Learning Constant
Faraj, Nathan
Machine Learning
This paper introduces a novel method for optimizing learning rates in machine learning. A previously unrecognized proportionality between learning rates and dataset sizes is discovered, providing valuable insights into how dataset scale influences training dynamics. Additionally, a cumulative learning constant is identified, offering a framework for designing and optimizing advanced learning rate schedules. These findings have the potential to enhance training efficiency and performance across a wide range of machine learning applications.
title Tuning Learning Rates with the Cumulative-Learning Constant
topic Machine Learning
url https://arxiv.org/abs/2505.13457