English
Related papers

Related papers: Experiments with Rich Regime Training for Deep Lea…

200 papers

Explaining the generalization characteristics of deep learning is an emerging topic in advanced machine learning. There are several unanswered questions about how learning under stochastic optimization really works and why certain…

Machine Learning · Computer Science 2022-04-01 Mahdi S. Hosseini , Mathieu Tuli , Konstantinos N. Plataniotis

In this paper, we study the sharpness of a deep learning (DL) loss landscape around local minima in order to reveal systematic mechanisms underlying the generalization abilities of DL models. Our analysis is performed across varying network…

Machine Learning · Computer Science 2022-02-07 Devansh Bisla , Jing Wang , Anna Choromanska

It is widely believed that stochastic gradient descent (SGD) performs significantly worse than adaptive optimizers such as Adam in pre-training Large Language Models (LLMs). Yet the underlying reason for this gap remains unclear. In this…

Machine Learning · Computer Science 2026-05-19 Athanasios Glentis , Dawei Li , Chung-Yiu Yau , Mingyi Hong

LLM training is resource-intensive. Quantized training improves computational and memory efficiency but introduces quantization noise, which can hinder convergence and degrade model accuracy. Stochastic Rounding (SR) has emerged as a…

Machine Learning · Computer Science 2025-11-04 Taowen Liu , Marta Andronic , Deniz Gündüz , George A. Constantinides

State-of-the-art training algorithms for deep learning models are based on stochastic gradient descent (SGD). Recently, many variations have been explored: perturbing parameters for better accuracy (such as in Extragradient), limiting SGD…

Machine Learning · Computer Science 2022-03-23 Amirkeivan Mohtashami , Martin Jaggi , Sebastian U. Stich

In the training of over-parameterized model functions via gradient descent, sometimes the parameters do not change significantly and remain close to their initial values. This phenomenon is called lazy training, and motivates consideration…

Quantum Physics · Physics 2023-05-03 Erfan Abedi , Salman Beigi , Leila Taghavi

Synchronous stochastic gradient descent (SGD) is the most common method used for distributed training of deep learning models. In this algorithm, each worker shares its local gradients with others and updates the parameters using the…

Machine Learning · Computer Science 2020-09-22 Negar Foroutan Eghlidi , Martin Jaggi

Having similar behavior at training time and test time $-$ what we call a "What You See Is What You Get" (WYSIWYG) property $-$ is desirable in machine learning. Models trained with standard stochastic gradient descent (SGD), however, do…

Machine Learning · Computer Science 2022-10-19 Bogdan Kulynych , Yao-Yuan Yang , Yaodong Yu , Jarosław Błasiok , Preetum Nakkiran

Continuous-time models provide important insights into the training dynamics of optimization algorithms in deep learning. In this work, we establish a non-asymptotic convergence analysis of stochastic gradient Langevin dynamics (SGLD),…

Machine Learning · Computer Science 2026-01-30 Noah Oberweis , Semih Cayci

Learning rate scheduling plays a critical role in the optimization of deep neural networks, directly influencing convergence speed, stability, and generalization. While existing schedulers such as cosine annealing, cyclical learning rates,…

Machine Learning · Computer Science 2026-03-05 Ayush K. Varshney , Šarūnas Girdzijauskas , Konstantinos Vandikas , Aneta Vulgarakis Feljan

Giving up and starting over may seem wasteful in many situations such as searching for a target or training deep neural networks (DNNs). Our study, though, demonstrates that resetting from a checkpoint can significantly improve…

Machine Learning · Computer Science 2025-03-14 Youngkyoung Bae , Yeongwoo Song , Hawoong Jeong

The training dynamics of linear networks are well studied in two distinct setups: the lazy regime and balanced/active regime, depending on the initialization and width of the network. We provide a surprisingly simple unifying formula for…

Machine Learning · Computer Science 2024-10-31 Zhenfeng Tu , Santiago Aranguri , Arthur Jacot

Recently many first and second order variants of SGD have been proposed to facilitate training of Deep Neural Networks (DNNs). A common limitation of these works stem from the fact that they use the same learning rate across all instances…

Machine Learning · Computer Science 2021-05-31 Shreyas Saxena , Nidhi Vyas , Dennis DeCoste

Motivated by extreme multi-label classification applications, we consider training deep learning models over sparse data in multi-GPU servers. The variance in the number of non-zero features across training batches and the intrinsic GPU…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-10-15 Yujing Ma , Florin Rusu , Kesheng Wu , Alexander Sim

Deep neural networks (DNNs) have demonstrated dominating performance in many fields; since AlexNet, networks used in practice are going wider and deeper. On the theoretical side, a long line of works has been focusing on training neural…

Machine Learning · Computer Science 2019-06-18 Zeyuan Allen-Zhu , Yuanzhi Li , Zhao Song

Machine learning models trained with \emph{stochastic} gradient descent (SGD) can generalize better than those trained with deterministic gradient descent (GD). In this work, we study SGD's impact on generalization through the lens of the…

Machine Learning · Computer Science 2025-12-09 Hongjian Lan , Yucong Liu , Florian Schäfer

Despite overparameterization, deep networks trained via supervised learning are easy to optimize and exhibit excellent generalization. One hypothesis to explain this is that overparameterized deep networks enjoy the benefits of implicit…

Machine Learning · Computer Science 2021-12-10 Aviral Kumar , Rishabh Agarwal , Tengyu Ma , Aaron Courville , George Tucker , Sergey Levine

Temporal Difference (TD) algorithms are widely used in Deep Reinforcement Learning (RL). Their performance is heavily influenced by the size of the neural network. While in supervised learning, the regime of over-parameterization and its…

Machine Learning · Computer Science 2024-02-20 David Brellmann , Eloïse Berthier , David Filliat , Goran Frehse

To reduce the long training time of large deep neural network (DNN) models, distributed synchronous stochastic gradient descent (S-SGD) is commonly used on a cluster of workers. However, the speedup brought by multiple workers is limited by…

Machine Learning · Computer Science 2020-03-03 Shaohuai Shi , Zhenheng Tang , Qiang Wang , Kaiyong Zhao , Xiaowen Chu

Stagewise training strategy is widely used for learning neural networks, which runs a stochastic algorithm (e.g., SGD) starting with a relatively large step size (aka learning rate) and geometrically decreasing the step size after a number…

Machine Learning · Statistics 2019-02-05 Zhuoning Yuan , Yan Yan , Rong Jin , Tianbao Yang