Increasing Both Batch Size and Learning Rate Accelerates Stochastic Gradient Descent

Hikaru Umeda, Hideaki Iiduka

Keywords: acceleration, batch size, deep learning, empirical risk minimization, learning rate, mini-batch SGD

TL;DR: Increasing Both Batch Size and Learning Rate Accelerates Stochastic Gradient Descent

Abstract:

The performance of mini-batch stochastic gradient descent (SGD) strongly depends on setting the batch size and learning rate to minimize the empirical loss in training the deep neural network.
In this paper, we present theoretical analyses of mini-batch SGD with four schedulers:
(i) constant batch size and decaying learning rate scheduler,
(ii) increasing batch size and decaying learning rate scheduler,
(iii) increasing batch size and increasing learning rate scheduler,
and
(iv) increasing batch size and warm-up decaying learning rate scheduler.
We show that mini-batch SGD using scheduler (i) does not always minimize the expectation of the full gradient norm of the empirical loss, whereas it does using any of schedulers (ii), (iii), and (iv).
Furthermore, schedulers (iii) and (iv) accelerate mini-batch SGD.
The paper also provides numerical results of supporting analyses showing that using scheduler (iii) or (iv) minimizes the full gradient norm of the empirical loss faster than using scheduler (i) or (ii).

Primary Area: optimization

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 1269