Skip to content

Source code for NeurIPS-2024 paper "Where Do Large Learnin Rates Lead Us"

License

Notifications You must be signed in to change notification settings

isadrtdinov/understanding-large-lrs

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Where Do Large Learning Rates Lead Us?

This repo is the official source code of NeurIPS-2024 paper:

Where Do Large Learning Rates Lead Us?
By Ildus Sadrtdinov*, Maxim Kodryan*, Eduard Pokonechny*, Ekaterina Lobacheva†, Dmitry Vetrov

* — equal contribution; † — shared senior authorship

arXiv / OpenReview: TBA / Poster & video: TBA

Abstract

It is generally accepted that starting neural networks training with large learning rates (LRs) improves generalization. Following a line of research devoted to understanding this effect, we conduct an empirical study in a controlled setting focusing on two questions: 1) how large an initial LR is required for obtaining optimal quality, and 2) what are the key differences between models trained with different LRs? We discover that only a narrow range of initial LRs slightly above the convergence threshold lead to optimal results after fine-tuning with a small LR or weight averaging. By studying the local geometry of reached minima, we observe that using LRs from this optimal range allows for the optimization to locate a basin that only contains high-quality minima. Additionally, we show that these initial LRs result in a sparse set of learned features, with a clear focus on those most relevant for the task. In contrast, starting training with too small LRs leads to unstable minima and attempts to learn all features simultaneously, resulting in poor generalization. Conversely, using initial LRs that are too large fails to detect a basin with good solutions and extract meaningful patterns from the data.

Code

About

Source code for NeurIPS-2024 paper "Where Do Large Learnin Rates Lead Us"

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published