English
Related papers

Related papers: Why Do We Need Warm-up? A Theoretical Perspective

200 papers

Learning rate warmup is a popular and practical technique in training large-scale deep neural networks. Despite the huge success in practice, the theoretical advantages of this strategy of gradually increasing the learning rate at the…

Machine Learning · Computer Science 2025-09-10 Yuxing Liu , Yuze Ge , Rui Pan , An Kang , Tong Zhang

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

We study adaptive learning rate scheduling for norm-constrained optimizers (e.g., Muon and Lion). We introduce a generalized smoothness assumption under which local curvature decreases with the suboptimality gap and empirically verify that…

Machine Learning · Computer Science 2026-05-19 Artem Riabinin , Andrey Veprikov , Arman Bolatov , Martin Takáč , Aleksandr Beznosikov

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

The Transformer is widely used in natural language processing tasks. To train a Transformer however, one usually needs a carefully designed learning rate warm-up stage, which is shown to be crucial to the final performance but will slow…

Machine Learning · Computer Science 2020-06-30 Ruibin Xiong , Yunchang Yang , Di He , Kai Zheng , Shuxin Zheng , Chen Xing , Huishuai Zhang , Yanyan Lan , Liwei Wang , Tie-Yan Liu

In many real-world deployments of machine learning systems, data arrive piecemeal. These learning scenarios may be passive, where data arrive incrementally due to structural properties of the problem (e.g., daily financial data) or active,…

Machine Learning · Computer Science 2021-01-01 Jordan T. Ash , Ryan P. Adams

The learning rate warmup heuristic achieves remarkable success in stabilizing training, accelerating convergence and improving generalization for adaptive stochastic optimization algorithms like RMSprop and Adam. Here, we study its…

Machine Learning · Computer Science 2021-10-27 Liyuan Liu , Haoming Jiang , Pengcheng He , Weizhu Chen , Xiaodong Liu , Jianfeng Gao , Jiawei Han

In this work, we study the evolution of the loss Hessian across many classification tasks in order to understand the effect the curvature of the loss has on the training dynamics. Whereas prior work has focused on how different learning…

Adaptive optimization algorithms such as Adam are widely used in deep learning. The stability of such algorithms is often improved with a warmup schedule for the learning rate. Motivated by the difficulty of choosing and tuning warmup…

Machine Learning · Computer Science 2021-03-23 Jerry Ma , Denis Yarats

We provide a theoretical explanation for the effectiveness of gradient clipping in training deep neural networks. The key ingredient is a new smoothness condition derived from practical neural network training examples. We observe that…

Optimization and Control · Mathematics 2020-02-12 Jingzhao Zhang , Tianxing He , Suvrit Sra , Ali Jadbabaie

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

Training recurrent neural networks is known to be difficult when time dependencies become long. In this work, we show that most standard cells only have one stable equilibrium at initialisation, and that learning on tasks with long time…

Machine Learning · Computer Science 2023-08-22 Gaspard Lambrechts , Florent De Geeter , Nicolas Vecoven , Damien Ernst , Guillaume Drion

Learning rate (LR) schedules in large language model (LLM) training often follow empirical templates: warm-up, constant plateau/stable phase, and decay (WSD). However, the mechanistic explanation for this strategy remains underexplored, and…

Artificial Intelligence · Computer Science 2025-07-08 Sibei Liu , Zhijian Hu

Designing effective reasoning-capable LLMs typically requires training using Reinforcement Learning with Verifiable Rewards (RLVR) or distillation with carefully curated Long Chain of Thoughts (CoT), both of which depend heavily on…

Artificial Intelligence · Computer Science 2026-02-02 Safal Shrestha , Minwu Kim , Aadim Nepal , Anubhav Shrestha , Keith Ross

Training deep neural networks using a large batch size has shown promising results and benefits many real-world applications. However, the optimizer converges slowly at early epochs and there is a gap between large-batch deep learning…

Machine Learning · Computer Science 2020-02-06 Zhouyuan Huo , Bin Gu , Heng Huang

Gradient regularization (GR), which aims to penalize the gradient norm atop the loss function, has shown promising results in training modern over-parameterized deep neural networks. However, can we trust this powerful technique? This paper…

Machine Learning · Computer Science 2024-06-17 Yang Zhao , Hao Zhang , Xiuyuan Hu

Model growth from a given checkpoint aims to accelerate training of a larger model, offering potential resource savings. Despite recent interest, warmstarting has seen limited practical adoption in large-scale training. We attribute this to…

We show that learning-rate schedules for large model training behave surprisingly similar to a performance bound from non-smooth convex optimization theory. We provide a bound for the constant schedule with linear cooldown; in particular,…

Machine Learning · Computer Science 2025-07-24 Fabian Schaipp , Alexander Hägele , Adrien Taylor , Umut Simsekli , Francis Bach

Transformer architectures serve as the backbone for most modern Large Language Models, therefore their pretraining stability and convergence speed are of central concern. Motivated by the logical dependency of sequentially stacked layers,…

Computation and Language · Computer Science 2026-03-06 Tianhao Chen , Xin Xu , Lu Yin , Hao Chen , Yang Wang , Shizhe Diao , Can Yang

This study delves into the plasticity of neural networks, offering empirical support for the notion that critical learning periods and warm-starting performance loss can be avoided through simple adjustments to learning hyperparameters. The…

Machine Learning · Computer Science 2025-10-14 Stanisław Pawlak
‹ Prev 1 2 3 10 Next ›