English
Related papers

Related papers: When and Why Momentum Accelerates SGD:An Empirical…

200 papers

The stochastic gradient descent (SGD) optimization algorithm plays a central role in a series of machine learning applications. The scientific literature provides a vast amount of upper error bounds for the SGD method. Much less attention…

Numerical Analysis · Mathematics 2020-10-05 Arnulf Jentzen , Philippe von Wurstemberger

In this work, we comprehensively reveal the learning dynamics of neural network with normalization, weight decay (WD), and SGD (with momentum), named as Spherical Motion Dynamics (SMD). Most related works study SMD by focusing on "effective…

Machine Learning · Statistics 2020-11-30 Ruosi Wan , Zhanxing Zhu , Xiangyu Zhang , Jian Sun

Stochastic difference-of-convex (DC) optimization is prevalent in numerous machine learning applications, yet its convergence properties under small batch sizes remain poorly understood. Existing methods typically require large batches or…

Machine Learning · Computer Science 2025-10-21 El Mahdi Chayti , Martin Jaggi

The article examines in some detail the convergence rate and mean-square-error performance of momentum stochastic gradient methods in the constant step-size and slow adaptation regime. The results establish that momentum methods are…

Optimization and Control · Mathematics 2016-10-13 Kun Yuan , Bicheng Ying , Ali H. Sayed

Stochastic Gradient Descent (SGD) often slows in the late stage of training due to anisotropic curvature and gradient noise. We analyze preconditioned SGD in the geometry induced by a symmetric positive definite matrix $\mathbf{M}$,…

Numerical Analysis · Mathematics 2025-11-26 Mitchell Scott , Tianshi Xu , Ziyuan Tang , Alexandra Pichette-Emmons , Qiang Ye , Yousef Saad , Yuanzhe Xi

It is well-known that stochastic gradient noise (SGN) acts as implicit regularization for deep learning and is essentially important for both optimization and generalization of deep networks. Some works attempted to artificially simulate…

Machine Learning · Computer Science 2022-08-31 Zeke Xie , Li Yuan , Zhanxing Zhu , Masashi Sugiyama

Motivated by broad applications in machine learning, we study the popular accelerated stochastic gradient descent (ASGD) algorithm for solving (possibly nonconvex) optimization problems. We characterize the finite-time performance of this…

Optimization and Control · Mathematics 2020-10-20 Thinh T. Doan , Lam M. Nguyen , Nhan H. Pham , Justin Romberg

We investigate the inherent bias of Stochastic Gradient Descent (SGD) toward learning low-rank weight matrices during the training of deep neural networks. Our results demonstrate that training with mini-batch SGD and weight decay induces a…

Machine Learning · Computer Science 2024-10-22 Tomer Galanti , Zachary S. Siegel , Aparna Gupte , Tomaso Poggio

The unprecedented growth of deep learning models has enabled remarkable advances but introduced substantial computational bottlenecks. A key factor contributing to training efficiency is batch-size and learning-rate scheduling in stochastic…

Machine Learning · Computer Science 2025-08-08 Hikaru Umeda , Hideaki Iiduka

We show that stochastic gradient descent (SGD) escapes from sharp minima exponentially fast even before SGD reaches stationary distribution. SGD has been a de-facto standard training algorithm for various machine learning tasks. However,…

Machine Learning · Computer Science 2022-03-22 Hikaru Ibayashi , Masaaki Imaizumi

Modern machine learning is trained by stochastic gradient descent (SGD), whose performance critically depends on how the learning rate (LR) is adjusted and decreased over time. Yet existing LR regimes may be intricate, or need to tune one…

Machine Learning · Computer Science 2025-08-20 Zhuang Yang

In this paper, we propose and analyze SQuARM-SGD, a communication-efficient algorithm for decentralized training of large-scale machine learning models over a network. In SQuARM-SGD, each node performs a fixed number of local SGD steps…

Machine Learning · Computer Science 2021-10-12 Navjot Singh , Deepesh Data , Jemin George , Suhas Diggavi

Stochastic gradient descent (SGD) still is the workhorse for many practical problems. However, it converges slow, and can be difficult to tune. It is possible to precondition SGD to accelerate its convergence remarkably. But many attempts…

Machine Learning · Statistics 2017-02-23 Xi-Lin Li

Local SGD is a communication-efficient variant of SGD for large-scale training, where multiple GPUs perform SGD independently and average the model parameters periodically. It has been recently observed that Local SGD can not only achieve…

Machine Learning · Computer Science 2023-03-10 Xinran Gu , Kaifeng Lyu , Longbo Huang , Sanjeev Arora

Stochastic gradient descent (SGD) gives an optimal convergence rate when minimizing convex stochastic objectives $f(x)$. However, in terms of making the gradients small, the original SGD does not give an optimal rate, even when $f(x)$ is…

Machine Learning · Computer Science 2021-07-30 Zeyuan Allen-Zhu

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

Stochastic Gradient Descent (SGD), a widely used optimization algorithm in deep learning, is often limited to converging to local optima due to the non-convex nature of the problem. Leveraging these local optima to improve model performance…

Machine Learning · Computer Science 2023-09-22 Hao Chen , Yusen Wu , Phuong Nguyen , Chao Liu , Yelena Yesha

We develop a new algorithm for non-convex stochastic optimization that finds an $\epsilon$-critical point in the optimal $O(\epsilon^{-3})$ stochastic gradient and Hessian-vector product computations. Our algorithm uses Hessian-vector…

Machine Learning · Computer Science 2021-07-13 Hoang Tran , Ashok Cutkosky

We analyze (stochastic) gradient descent (SGD) with delayed updates on smooth quasi-convex and non-convex functions and derive concise, non-asymptotic, convergence rates. We show that the rate of convergence in all cases consists of two…

Machine Learning · Computer Science 2021-06-17 Sebastian U. Stich , Sai Praneeth Karimireddy

Stochastic gradient descent (SGD) is central to deep learning, yet the dynamical origin of its preference for flatter, more generalizable solutions remains unclear. Here, by analyzing SGD learning dynamics, we identify a nonequilibrium…

Machine Learning · Computer Science 2026-01-19 Ning Yang , Yikuan Zhang , Qi Ouyang , Chao Tang , Yuhai Tu