English
Related papers

Related papers: Large Batch Training Does Not Need Warmup

200 papers

Recently the LARS and LAMB optimizers have been proposed for training neural networks faster using large batch sizes. LARS and LAMB add layer-wise normalization to the update rules of Heavy-ball momentum and Adam, respectively, and have…

Machine Learning · Computer Science 2021-06-11 Zachary Nado , Justin M. Gilmer , Christopher J. Shallue , Rohan Anil , George E. Dahl

Recently, sparse training methods have started to be established as a de facto approach for training and inference efficiency in artificial neural networks. Yet, this efficiency is just in theory. In practice, everyone uses a binary mask to…

Machine Learning · Computer Science 2022-07-13 Selima Curci , Decebal Constantin Mocanu , Mykola Pechenizkiyi

Training a large-scale deep neural network in a large-scale dataset is challenging and time-consuming. The recent breakthrough of large-batch optimization is a promising way to tackle this challenge. However, although the current advanced…

Computer Vision and Pattern Recognition · Computer Science 2022-10-21 Zeyue Xue , Jianming Liang , Guanglu Song , Zhuofan Zong , Liang Chen , Yu Liu , Ping Luo

Learning Rate Warmup is a popular heuristic for training neural networks, especially at larger batch sizes, despite limited understanding of its benefits. Warmup decreases the update size $\Delta \mathbf{w}_t = \eta_t \mathbf{u}_t$ early in…

Machine Learning · Computer Science 2024-11-01 Atli Kosson , Bettina Messmer , Martin Jaggi

Batch normalization is a key component of most image classification models, but it has many undesirable properties stemming from its dependence on the batch size and interactions between examples. Although recent work has succeeded in…

Computer Vision and Pattern Recognition · Computer Science 2021-02-12 Andrew Brock , Soham De , Samuel L. Smith , Karen Simonyan

Training deep neural networks--and more recently, large models demands efficient and scalable optimizers. Adaptive gradient algorithms like Adam, AdamW, and their variants have been central to this task. Despite the development of numerous…

Machine Learning · Computer Science 2025-09-05 Huizhuo Yuan , Yifeng Liu , Shuang Wu , Xun Zhou , Quanquan Gu

Recent works demonstrate that early layers in a neural network contain useful information for prediction. Inspired by this, we show that extending temperature scaling across all layers improves both calibration and accuracy. We call this…

Machine Learning · Computer Science 2022-11-21 Amr Khalifa , Michael C. Mozer , Hanie Sedghi , Behnam Neyshabur , Ibrahim Alabdulmohsin

Scale of data and scale of computation infrastructures together enable the current deep learning renaissance. However, training large-scale deep architectures demands both algorithmic improvement and careful system configuration. In this…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-09-21 Shang-Xuan Zou , Chun-Yen Chen , Jui-Lin Wu , Chun-Nan Chou , Chia-Chin Tsao , Kuan-Chieh Tung , Ting-Wei Lin , Cheng-Lung Sung , Edward Y. Chang

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to start the process over again once new data becomes available. A much more efficient solution is to continually pre-train these models, saving significant…

As models for nature language processing (NLP), computer vision (CV) and recommendation systems (RS) require surging computation, a large number of GPUs/TPUs are paralleled as a large batch (LB) to improve training throughput. However,…

Machine Learning · Computer Science 2023-09-26 Guo-qing Jiang , Jinlong Liu , Zixiang Ding , Lin Guo , Wei Lin

The training process of neural networks is known to be time-consuming, and having a deep architecture only aggravates the issue. This process consists mostly of matrix operations, among which matrix multiplication is the bottleneck. Several…

Machine Learning · Computer Science 2025-06-17 Sana Ebrahimi , Rishi Advani , Abolfazl Asudeh

As deep learning models and datasets rapidly scale up, network training is extremely time-consuming and resource-costly. Instead of training on the entire dataset, learning with a small synthetic dataset becomes an efficient solution.…

Machine Learning · Computer Science 2022-08-02 Zixuan Jiang , Jiaqi Gu , Mingjie Liu , David Z. Pan

Fast and efficient AI inference is increasingly important, and recent models that directly learn low-level logic operations have achieved state-of-the-art performance. However, existing logic neural networks incur high training costs,…

Machine Learning · Computer Science 2026-02-04 Lino Gerlach , Thore Gerlach , Liv Våge , Elliott Kauffman , Isobel Ojalvo

Deep neural networks (DNNs) are often trained on the premise that the complete training data set is provided ahead of time. However, in real-world scenarios, data often arrive in chunks over time. This leads to important considerations…

Machine Learning · Computer Science 2023-03-21 Vijaya Raghavan T. Ramkumar , Elahe Arani , Bahram Zonooz

Deep neural networks may perform poorly when training datasets are heavily class-imbalanced. Recently, two-stage methods decouple representation learning and classifier learning to improve performance. But there is still the vital issue of…

Computer Vision and Pattern Recognition · Computer Science 2021-04-02 Zhisheng Zhong , Jiequan Cui , Shu Liu , Jiaya Jia

Graph neural networks (GNNs), which learn the node representations by recursively aggregating information from its neighbors, have become a predominant computational tool in many domains. To handle large-scale graphs, most of the existing…

Machine Learning · Computer Science 2021-09-01 Kaixiong Zhou , Ninghao Liu , Fan Yang , Zirui Liu , Rui Chen , Li Li , Soo-Hyun Choi , Xia Hu

It is common in deep learning to warm up the learning rate $\eta$, often by a linear schedule between $\eta_{\text{init}} = 0$ and a predetermined target $\eta_{\text{trgt}}$. In this paper, we show through systematic experiments using SGD…

Machine Learning · Computer Science 2024-11-05 Dayal Singh Kalra , Maissam Barkeshli

Distributed machine learning is critical for training deep learning models on large datasets with numerous parameters. Current research primarily focuses on leveraging additional hardware resources and powerful computing units to accelerate…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-03 Kuan-Wei Lu , Ding-Yong Hong , Pangfeng Liu , Jan-Jan Wu

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

Training large-scale models presents challenges not only in terms of resource requirements but also in terms of their convergence. For this reason, the learning rate (LR) is often decreased when the size of a model is increased. Such a…

Computation and Language · Computer Science 2025-05-30 Marco Gaido , Sara Papi , Luisa Bentivogli , Alessio Brutti , Mauro Cettolo , Roberto Gretter , Marco Matassoni , Mohamed Nabih , Matteo Negri