English
Related papers

Related papers: Why (and When) does Local SGD Generalize Better th…

200 papers

The notion of implicit bias, or implicit regularization, has been suggested as a means to explain the surprising generalization ability of modern-days overparameterized learning algorithms. This notion refers to the tendency of the…

Machine Learning · Computer Science 2020-12-23 Assaf Dauber , Meir Feder , Tomer Koren , Roi Livni

Uniform stability is a notion of algorithmic stability that bounds the worst case change in the model output by the algorithm when a single data point in the dataset is replaced. An influential work of Hardt et al. (2016) provides strong…

Machine Learning · Computer Science 2020-06-15 Raef Bassily , Vitaly Feldman , Cristóbal Guzmán , Kunal Talwar

Large-scale distributed training of deep acoustic models plays an important role in today's high-performance automatic speech recognition (ASR). In this paper we investigate a variety of asynchronous decentralized distributed training…

Computation and Language · Computer Science 2021-10-22 Xiaodong Cui , Wei Zhang , Abdullah Kayi , Mingrui Liu , Ulrich Finkler , Brian Kingsbury , George Saon , David Kung

Distributed training is an effective way to accelerate the training process of large-scale deep learning models. However, the parameter exchange and synchronization of distributed stochastic gradient descent introduce a large amount of…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-08-16 LingFei Dai , Boyu Diao , Chao Li , Yongjun Xu

Existing research shows that the batch size can seriously affect the performance of stochastic gradient descent~(SGD) based learning, including training speed and generalization ability. A larger batch size typically results in less…

Machine Learning · Statistics 2020-02-28 Shen-Yi Zhao , Yin-Peng Xie , Wu-Jun Li

While significant theoretical progress has been achieved, unveiling the generalization mystery of overparameterized neural networks still remains largely elusive. In this paper, we study the generalization behavior of shallow neural…

Machine Learning · Computer Science 2022-09-21 Yunwen Lei , Rong Jin , Yiming Ying

The performance of mini-batch stochastic gradient descent (SGD) strongly depends on setting the batch size and learning rate to minimize the empirical loss in training the deep neural network. In this paper, we present theoretical analyses…

Machine Learning · Computer Science 2025-02-17 Hikaru Umeda , Hideaki Iiduka

We consider a variant of the stochastic gradient descent (SGD) with a random learning rate and reveal its convergence properties. SGD is a widely used stochastic optimization algorithm in machine learning, especially deep learning. Numerous…

Machine Learning · Statistics 2025-09-09 Naoki Yoshida , Shogo Nakakita , Masaaki Imaizumi

The existing analysis of asynchronous stochastic gradient descent (SGD) degrades dramatically when any delay is large, giving the impression that performance depends primarily on the delay. On the contrary, we prove much better guarantees…

Optimization and Control · Mathematics 2023-04-21 Konstantin Mishchenko , Francis Bach , Mathieu Even , Blake Woodworth

Hierarchical SGD (H-SGD) has emerged as a new distributed SGD algorithm for multi-level communication networks. In H-SGD, before each global aggregation, workers send their updated local models to local servers for aggregations. Despite…

Machine Learning · Computer Science 2024-04-12 Jiayi Wang , Shiqiang Wang , Rong-Rong Chen , Mingyue Ji

The implementation of a vast majority of machine learning (ML) algorithms boils down to solving a numerical optimization problem. In this context, Stochastic Gradient Descent (SGD) methods have long proven to provide good results, both in…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-10-06 Janis Keuper , Franz-Josef Pfreundt

We showcase important features of the dynamics of the Stochastic Gradient Descent (SGD) in the training of neural networks. We present empirical observations that commonly used large step sizes (i) lead the iterates to jump from one side of…

Machine Learning · Computer Science 2023-06-08 Maksym Andriushchenko , Aditya Varre , Loucas Pillaud-Vivien , Nicolas Flammarion

Why does training deep neural networks using stochastic gradient descent (SGD) result in a generalization error that does not worsen with the number of parameters in the network? To answer this question, we advocate a notion of effective…

Machine Learning · Computer Science 2019-01-15 Vaishnavh Nagarajan , J. Zico Kolter

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

Large-batch SGD is important for scaling training of deep neural networks. However, without fine-tuning hyperparameter schedules, the generalization of the model may be hampered. We propose to use batch augmentation: replicating instances…

Machine Learning · Computer Science 2019-01-29 Elad Hoffer , Tal Ben-Nun , Itay Hubara , Niv Giladi , Torsten Hoefler , Daniel Soudry

Distributed stochastic optimization intertwines (i) stochastic gradient noise, (ii) communication compression, and (iii) adaptive/normalized updates. While each factor has been studied in isolation, their joint effect under realistic…

Stochastic Gradient Descent (SGD) is a widely deployed optimization procedure throughout data-driven and simulation-driven disciplines, which has drawn a substantial interest in understanding its global behavior across a broad class of…

Optimization and Control · Mathematics 2021-04-02 Vivak Patel , Shushu Zhang

A longstanding debate surrounds the related hypotheses that low-curvature minima generalize better, and that SGD discourages curvature. We offer a more complete and nuanced view in support of both. First, we show that curvature harms test…

Machine Learning · Statistics 2022-07-29 Arwen V. Bradley , Carlos Alberto Gomez-Uribe , Manish Reddy Vuyyuru

Low-precision training has become crucial for reducing the computational and memory costs of large-scale deep learning. However, quantizing gradients introduces magnitude shrinkage, which can change how stochastic gradient descent (SGD)…

Machine Learning · Computer Science 2026-01-09 Vincent-Daniel Yun

Recent developments on large-scale distributed machine learning applications, e.g., deep neural networks, benefit enormously from the advances in distributed non-convex optimization techniques, e.g., distributed Stochastic Gradient Descent…

Optimization and Control · Mathematics 2019-05-13 Hao Yu , Rong Jin , Sen Yang