paper-with-me

홈 › Papers

Batch size invariant Adam

2024-02-29 · Xi Wang, Laurence Aitchison

We propose a batch size invariant version of Adam, for use in large-scale, distributed settings, in which the mini-batch is divided into micro-batches which are distributed among worker nodes. For the v term, standard Adam first computes the average over micro-batch gradients, then squares, while in the batch size invariant Adam proposed here, we first square the micro-batch gradients, then average. Previous work (e.g. Malladi et al. 2022) used an alternative approach that involved a square-root scaling of the learning rate, but this approach requires strong assumptions to work; in particular that the gradient variance dominates the square of the expected gradient. In contrast, the approach proposed here gives batch size invariance without this assumption. We confirm that in practice our scheme gives batch size invariance in a much larger range of scenarios than the previous approach.

📄 PDF Abstract BibTeX arXiv:2402.18824

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Adam 설명 없음

Similar Papers 제목 키워드 기반

Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch Regime

2025-10-30 · Beomhan Baek, Minhak Song, Chulhee Yun arxiv

Adam [Kingma & Ba, 2015] is the de facto optimizer in deep learning, yet its theoretical understanding remains limited. Prior analyses show that Adam favors solutions aligned with $\ell_\infty$-geometry, but these result…

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks

2025-10-13 · Xuan Tang, Han Zhang, Yuan Cao, Difan Zou arxiv

Adam is a popular and widely used adaptive gradient method in deep learning, which has also received tremendous focus in theoretical research. However, most existing theoretical work primarily analyzes its full-batch ver…

Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration

2021-01-14 · Congliang Chen, Li Shen, Fangyu Zou, Wei Liu

Adam is one of the most influential adaptive stochastic algorithms for training deep neural networks, which has been pointed out to be divergent even in the simple convex setting via a few simple counterexamples. Many at…

Stochastic Optimization

Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling

2024-05-23 · Shuaipeng Li, Penghao Zhao, Hailin Zhang, Xingwu Sun 외

In current deep learning tasks, Adam style optimizers such as Adam, Adagrad, RMSProp, Adafactor, and Lion have been widely used as alternatives to SGD style optimizers. These optimizers typically update model parameters …

Is your batch size the problem? Revisiting the Adam-SGD gap in language modeling

2025-06-14 · Teodora Srećković, Jonas Geiping, Antonio Orvieto

Adam is known to perform significantly better than Stochastic Gradient Descent (SGD) in language models, a phenomenon for which a number of explanations have been proposed. In this work, we revisit this "optimizer gap" t…

Language ModelingLanguage Modelling