English
Related papers

Related papers: Subsampling is not Magic: Why Large Batch Sizes Wo…

200 papers

Stochastic Gradient Descent (SGD) is a popular tool in training large-scale machine learning models. Its performance, however, is highly variable, depending crucially on the choice of the step sizes. Accordingly, a variety of strategies for…

Machine Learning · Statistics 2021-06-11 Xiaoyu Li , Zhenxun Zhuang , Francesco Orabona

Variance-reduced algorithms, although achieve great theoretical performance, can run slowly in practice due to the periodic gradient estimation with a large batch of data. Batch-size adaptation thus arises as a promising approach to…

Optimization and Control · Mathematics 2020-07-28 Kaiyi Ji , Zhe Wang , Bowen Weng , Yi Zhou , Wei Zhang , Yingbin Liang

Stochastic gradient descent (SGD) is central to simulation optimization, stochastic programming, and online M-estimation, where sampling effort is a decision variable. We study the mini-batch gradient noise as a sampling-design object.…

Machine Learning · Statistics 2026-04-16 Daniel Zantedeschi , Kumar Muthuraman

We study the problem of differentially private linear regression where each data point is sampled from a fixed sub-Gaussian style distribution. We propose and analyze a one-pass mini-batch stochastic gradient descent method (DP-AMBSSGD)…

Machine Learning · Computer Science 2022-07-14 Prateek Varshney , Abhradeep Thakurta , Prateek Jain

Differentially private stochastic gradient descent (DP-SGD) adds noise to gradients in back-propagation, safeguarding training data from privacy leakage, particularly membership inference. It fails to cover (inference-time) threats like…

Cryptography and Security · Computer Science 2023-09-20 Minxin Du , Xiang Yue , Sherman S. M. Chow , Tianhao Wang , Chenyu Huang , Huan Sun

In this paper, we propose a stochastic optimization method that adaptively controls the sample size used in the computation of gradient approximations. Unlike other variance reduction techniques that either require additional storage or the…

Optimization and Control · Mathematics 2017-11-01 Raghu Bollapragada , Richard Byrd , Jorge Nocedal

We consider the stochastic gradient descent (SGD) algorithm driven by a general stochastic sequence, including i.i.d noise and random walk on an arbitrary graph, among others; and analyze it in the asymptotic sense. Specifically, we employ…

Machine Learning · Computer Science 2022-09-16 Jie Hu , Vishwaraj Doshi , Do Young Eun

The stochastic gradient descent (SGD) algorithm is the algorithm we use to train neural networks. However, it remains poorly understood how the SGD navigates the highly nonlinear and degenerate loss landscape of a neural network. In this…

Machine Learning · Computer Science 2025-06-13 Liu Ziyin , Hongchao Li , Masahito Ueda

Stochastic gradient descent (SGD) and adaptive gradient methods, such as Adam and RMSProp, have been widely used in training deep neural networks. We empirically show that while the difference between the standard generalization performance…

Machine Learning · Computer Science 2023-11-30 Avery Ma , Yangchen Pan , Amir-massoud Farahmand

Differential Privacy (DP) provides a formal privacy guarantee preventing adversaries with access to a machine learning model from extracting information about individual training points. Differentially Private Stochastic Gradient Descent…

Machine Learning · Computer Science 2022-06-17 Soham De , Leonard Berrada , Jamie Hayes , Samuel L. Smith , Borja Balle

Distributed Deep Learning (DDL) is essential for large-scale Deep Learning (DL) training. Synchronous Stochastic Gradient Descent (SSGD) 1 is the de facto DDL optimization method. Using a sufficiently large batch size is critical to…

Machine Learning · Computer Science 2021-12-03 Wei Zhang , Mingrui Liu , Yu Feng , Xiaodong Cui , Brian Kingsbury , Yuhai Tu

Stochastic gradient descent (SGD) is one of the most popular algorithms in modern machine learning. The noise encountered in these applications is different from that in many theoretical analyses of stochastic gradient algorithms. In this…

Machine Learning · Statistics 2021-09-16 Stephan Wojtowytsch

In this paper, we propose a novel approach to automatically determine the batch size in stochastic gradient descent methods. The choice of the batch size induces a trade-off between the accuracy of the gradient estimate and the cost in…

Machine Learning · Computer Science 2017-12-12 Matteo Pirotta , Marcello Restelli

Differentially Private Stochastic Gradient Descent (DP-SGD) is widely used to protect training data in machine learning. Its privacy guarantee is commonly analyzed through a security game in which an adversary infers whether a target record…

Cryptography and Security · Computer Science 2026-05-18 Wenhao Wang , Shujie Cui , Hui Cui , Xingliang Yuan

It is folklore that reusing training data more than once can improve the statistical efficiency of gradient-based learning. However, beyond linear regression, the theoretical advantage of full-batch gradient descent (GD, which always reuses…

Machine Learning · Statistics 2026-02-03 Filip Kovačević , Hong Chang Ji , Denny Wu , Mahdi Soltanolkotabi , Marco Mondelli

We study convergence rates of AdaGrad-Norm as an exemplar of adaptive stochastic gradient methods (SGD), where the step sizes change based on observed stochastic gradients, for minimizing non-convex, smooth objectives. Despite their…

Machine learning (ML) models trained by differentially private stochastic gradient descent (DP-SGD) have much lower utility than the non-private ones. To mitigate this degradation, we propose a DP Laplacian smoothing SGD (DP-LSSGD) to train…

Machine Learning · Computer Science 2019-12-10 Bao Wang , Quanquan Gu , March Boedihardjo , Farzin Barekat , Stanley J. Osher

Despite exceptional achievements, training neural networks remains computationally expensive and is often plagued by instabilities that can degrade convergence. While learning rate schedules can help mitigate these issues, finding optimal…

Machine Learning · Computer Science 2026-03-30 Benoit Dherin , Benny Avelin , Anders Karlsson , Hanna Mazzawi , Javier Gonzalvo , Michael Munn

The convergence behavior of mini-batch stochastic gradient descent (SGD) is highly sensitive to the batch size and learning rate settings. Recent theoretical studies have identified the existence of a critical batch size that minimizes…

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

We provide new lower bounds on the privacy guarantee of the multi-epoch Adaptive Batch Linear Queries (ABLQ) mechanism with shuffled batch sampling, demonstrating substantial gaps when compared to Poisson subsampling; prior analysis was…

Machine Learning · Computer Science 2024-11-08 Lynn Chua , Badih Ghazi , Pritish Kamath , Ravi Kumar , Pasin Manurangsi , Amer Sinha , Chiyuan Zhang