English
Related papers

Related papers: Why Warmup the Learning Rate? Underlying Mechanism…

200 papers

Deep Learning has revolutionized machine learning and artificial intelligence, achieving superhuman performance in several standard benchmarks. It is well-known that deep learning models are inefficient to train; they learn by processing…

Machine Learning · Computer Science 2021-12-03 Fartash Faghri

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

We consider neural networks (NNs) where the final layer is down-scaled by a fixed hyperparameter $\gamma$. Recent work has identified $\gamma$ as controlling the strength of feature learning. As $\gamma$ increases, network evolution changes…

Machine Learning · Computer Science 2025-03-04 Alexander Atanasov , Alexandru Meterez , James B. Simon , Cengiz Pehlevan

Beginning from a basic neural-network architecture, we test the potential benefits offered by a range of advanced techniques for machine learning, in particular deep learning, in the context of a typical classification problem encountered…

Data Analysis, Statistics and Probability · Physics 2020-06-03 Giles Chatham Strong

Momentum has become a crucial component in deep learning optimizers, necessitating a comprehensive understanding of when and why it accelerates stochastic gradient descent (SGD). To address the question of ''when'', we establish a…

Machine Learning · Computer Science 2023-06-16 Jingwen Fu , Bohan Wang , Huishuai Zhang , Zhizheng Zhang , Wei Chen , Nanning Zheng

Modern deep learning (DL) architectures are trained using variants of the SGD algorithm that is run with a $\textit{manually}$ defined learning rate schedule, i.e., the learning rate is dropped at the pre-defined epochs, typically when the…

Machine Learning · Computer Science 2021-12-14 Yunfei Teng , Jing Wang , Anna Choromanska

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

Deep learning's success has been attributed to the training of large, overparameterized models on massive amounts of data. As this trend continues, model training has become prohibitively costly, requiring access to powerful computing…

Machine Learning · Computer Science 2021-11-25 Ravi S Raju , Kyle Daruwalla , Mikko Lipasti

In this paper we propose to solve an important problem in recommendation -- user cold start, based on meta leaning method. Previous meta learning approaches finetune all parameters for each new user, which is both computing and storage…

Information Retrieval · Computer Science 2019-12-10 Liang Zhao , Yang Wang , Daxiang Dong , Hao Tian

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

This paper introduces a novel approach, Decision Theory-guided Deep Reinforcement Learning (DT-guided DRL), to address the inherent cold start problem in DRL. By integrating decision theory principles, DT-guided DRL enhances agents' initial…

Machine Learning · Computer Science 2024-02-12 Zelin Wan , Jin-Hee Cho , Mu Zhu , Ahmed H. Anwar , Charles Kamhoua , Munindar P. Singh

Deep learning have achieved promising results on a wide spectrum of AI applications. Larger datasets and models consistently yield better performance. However, we generally spend longer training time on more computation and communication.…

Machine Learning · Computer Science 2021-11-03 Xiaoxin He , Fuzhao Xue , Xiaozhe Ren , Yang You

Learning rate adaptation is a popular topic in machine learning. Gradient Descent trains neural nerwork with a fixed learning rate. Learning rate adaptation is proposed to accelerate the training process through adjusting the step size in…

Machine Learning · Computer Science 2022-10-20 Bozhou Chen , Hongzhi Wang , Chenmin Ba

Deploying deep learning on Synthetic Aperture Radar (SAR) data is becoming more common for mapping purposes. One such case is sea ice, which is highly dynamic and rapidly changes as a result of the combined effect of wind, temperature, and…

Computer Vision and Pattern Recognition · Computer Science 2023-10-27 Morteza Karimzadeh , Rafael Pires de Lima

Deep neural network training spends most of the computation on examples that are properly handled, and could be ignored. We propose to mitigate this phenomenon with a principled importance sampling scheme that focuses computation on…

Machine Learning · Computer Science 2019-10-29 Angelos Katharopoulos , François Fleuret

Most theoretical studies explaining the regularization effect in deep learning have only focused on gradient descent with a sufficient small learning rate or even gradient flow (infinitesimal learning rate). Such researches, however, have…

Machine Learning · Computer Science 2020-12-17 Wei Huang , Weitao Du , Richard Yi Da Xu , Chunrui Liu

Training Large Language Models (LLMs) incurs significant cost; hence, any strategy that accelerates model convergence is helpful. In this paper, we investigate the ability of a simple idea checkpoint averaging along the trajectory of a…

Machine Learning · Computer Science 2023-12-13 Sunny Sanyal , Atula Neerkaje , Jean Kaddour , Abhishek Kumar , Sujay Sanghavi

The start of deep neural network training is characterized by a brief yet critical phase that lasts from the beginning of the training until the accuracy reaches approximately 50\%. During this phase, disordered representations rapidly…

Machine Learning · Computer Science 2025-10-30 Tiantian Liu , Meng Wan , Jue Wang , Ningming Nie

We introduce a machine-learning framework to warm-start fixed-point optimization algorithms. Our architecture consists of a neural network mapping problem parameters to warm starts, followed by a predefined number of fixed-point iterations.…

Optimization and Control · Mathematics 2023-09-15 Rajiv Sambharya , Georgina Hall , Brandon Amos , Bartolomeo Stellato

We prove that for a broad class of permutation-equivariant learning rules (including SGD, Adam, and others), the training process induces a bi-Lipschitz mapping between neurons and strongly constrains the topology of the neuron distribution…

Machine Learning · Computer Science 2025-10-06 Yongyi Yang , Tomaso Poggio , Isaac Chuang , Liu Ziyin