English
Related papers

Related papers: Critical Batch Size Revisited: A Simple Empirical …

200 papers

Training large-scale models under given resources requires careful design of parallelism strategies. In particular, the efficiency notion of critical batch size (CBS), concerning the compromise between time and compute, marks the threshold…

Machine Learning · Computer Science 2025-04-22 Hanlin Zhang , Depen Morwani , Nikhil Vyas , Jingfeng Wu , Difan Zou , Udaya Ghai , Dean Foster , Sham Kakade

In an increasing number of domains it has been demonstrated that deep learning models can be trained using relatively large batch sizes without sacrificing data efficiency. However the limits of this massive data parallelism seem to differ…

Machine Learning · Computer Science 2018-12-18 Sam McCandlish , Jared Kaplan , Dario Amodei , OpenAI Dota Team

We study the role of batch size in stochastic conditional gradient methods under a $\mu$-Kurdyka-{\L}ojasiewicz ($\mu$-KL) condition. Focusing on momentum-based stochastic conditional gradient algorithms (e.g., Scion), we derive a new…

Machine Learning · Computer Science 2026-03-24 Rustem Islamov , Roman Machacek , Aurelien Lucchi , Antonio Silveti-Falls , Eduard Gorbunov , Volkan Cevher

Foundation models in speech are often trained using many GPUs, which implicitly leads to large effective batch sizes. In this paper we study the effect of batch size on pre-training, both in terms of statistics that can be monitored during…

Sound · Computer Science 2024-02-22 Nik Vaessen , David A. van Leeuwen

Large language models (LLMs) have made remarkable advances in recent years, with scaling laws playing a critical role in this rapid progress. In this paper, we empirically investigate how a critical hyper-parameter, i.e., the global batch…

Computation and Language · Computer Science 2024-12-03 Xian Shuai , Yiding Wang , Yimeng Wu , Xin Jiang , Xiaozhe Ren

Increasing the mini-batch size for stochastic gradient descent offers significant opportunities to reduce wall-clock training time, but there are a variety of theoretical and systems challenges that impede the widespread success of this…

Training large language models requires jointly configuring two interdependent aspects of the system: the global batch size, which governs statistical efficiency, and the 3D parallelism strategy, which governs hardware throughput. Existing…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-30 Akhmed Sakip , Erland Hilman Fuadi , Omar Sayedelahl , Zonghang Li , Jianshu She , Alham Fikri Aji , Steve Liu , Eric Xing , Qirong Ho

The performance of neural network-based speech enhancement systems is primarily influenced by the model architecture, whereas training times and computational resource utilization are primarily affected by training parameters such as the…

Sound · Computer Science 2023-11-09 Philippe Gonzalez , Tommy Sonne Alstrøm , Tobias May

We introduce Predictive Batch Scheduling (PBS), a novel training optimization technique that accelerates language model convergence by dynamically prioritizing high-loss samples during batch construction. Unlike curriculum learning…

Artificial Intelligence · Computer Science 2026-02-20 Sumedh Rasal

Increasing the batch size during training -- a ''batch ramp'' -- is a promising strategy to accelerate large language model pretraining. While for SGD, doubling the batch size can be equivalent to halving the learning rate, the optimal…

Machine Learning · Computer Science 2025-10-17 Alexandru Meterez , Depen Morwani , Jingfeng Wu , Costin-Andrei Oncescu , Cengiz Pehlevan , Sham Kakade

The concept of Critical Batch Size, as pioneered by OpenAI, has long served as a foundational principle for large-scale pre-training. However, with the paradigm shift towards the Warmup-Stable-Decay (WSD) learning rate scheduler, we observe…

Artificial Intelligence · Computer Science 2026-01-12 Yunhua Zhou , Junhao Huang , Shuhao Xing , Yechen Zhang , Runyu Peng , Qiping Guo , Xipeng Qiu

Increasing the batch size is a popular way to speed up neural network training, but beyond some critical batch size, larger batch sizes yield diminishing returns. In this work, we study how the critical batch size changes based on…

Recent works have demonstrated great success in pre-training large-scale autoregressive language models on massive GPUs. To reduce the wall-clock training time, a common practice is to increase the batch size and learning rate. However,…

Machine Learning · Computer Science 2022-10-18 Conglong Li , Minjia Zhang , Yuxiong He

Existing research shows that the batch size can seriously affect the performance of stochastic gradient descent~(SGD) based learning, including training speed and generalization ability. A larger batch size typically results in less…

Machine Learning · Statistics 2020-02-28 Shen-Yi Zhao , Yin-Peng Xie , Wu-Jun Li

Conventional wisdom dictates that small batch sizes make language model pretraining and fine-tuning unstable, motivating gradient accumulation, which trades off the number of optimizer steps for a proportional increase in batch size. While…

Machine Learning · Computer Science 2025-12-17 Martin Marek , Sanae Lotfi , Aditya Somasundaram , Andrew Gordon Wilson , Micah Goldblum

Practical results have shown that deep learning optimizers using small constant learning rates, hyperparameters close to one, and large batch sizes can find the model parameters of deep neural networks that minimize the loss functions. We…

Machine Learning · Computer Science 2022-08-23 Hideaki Iiduka

Mini-batch stochastic gradient descent and variants thereof have become standard for large-scale empirical risk minimization like the training of neural networks. These methods are usually used with a constant batch size chosen by simple…

Machine Learning · Computer Science 2017-06-29 Lukas Balles , Javier Romero , Philipp Hennig

Batch size scheduling (BSS) plays a critical role in large-scale deep learning training, influencing both optimization dynamics and computational efficiency. Yet, its theoretical foundations remain poorly understood. In this work, we show…

Machine Learning · Computer Science 2026-02-24 Jinbo Wang , Binghui Li , Zhanpeng Zhou , Mingze Wang , Yuxuan Sun , Jiaqi Zhang , Xunliang Cai , Lei Wu

Scaling laws are useful guides for derisking expensive training runs, as they predict performance of large models using cheaper, small-scale experiments. However, there remain gaps between current scaling studies and how language models are…

An appropriate choice of batch sizes in large-scale model training is crucial, yet it involves an intrinsic yet inevitable dilemma: large-batch training improves training efficiency in terms of memory utilization, while generalization…

Machine Learning · Computer Science 2025-03-18 Tim Tsz-Kit Lau , Weijian Li , Chenwei Xu , Han Liu , Mladen Kolar
‹ Prev 1 2 3 10 Next ›