English
Related papers

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

200 papers

This article examines the implicit regularization effect of Stochastic Gradient Descent (SGD). We consider the case of SGD without replacement, the variant typically used to optimize large-scale neural networks. We analyze this algorithm in…

Machine Learning · Computer Science 2024-04-23 Pierfrancesco Beneventano

Stochastic gradient descent (SGD) is a well known method for regression and classification tasks. However, it is an inherently sequential algorithm at each step, the processing of the current example depends on the parameters learned from…

Machine Learning · Computer Science 2017-05-24 Saeed Maleki , Madanlal Musuvathi , Todd Mytkowicz

Stochastic gradient descent (SGD) is a pillar of modern machine learning, serving as the go-to optimization algorithm for a diverse array of problems. While the empirical success of SGD is often attributed to its computational efficiency…

Machine Learning · Statistics 2022-06-16 Courtney Paquette , Elliot Paquette , Ben Adlam , Jeffrey Pennington

The performance of stochastic gradient descent (SGD) depends critically on how learning rates are tuned and decreased over time. We propose a method to automatically adjust multiple learning rates so as to minimize the expected error at any…

Machine Learning · Statistics 2013-02-19 Tom Schaul , Sixin Zhang , Yann LeCun

In this paper we study the problem of convergence and generalization error bound of stochastic momentum for deep learning from the perspective of regularization. To do so, we first interpret momentum as solving an $\ell_2$-regularized…

Machine Learning · Computer Science 2019-06-04 Ziming Zhang , Wenju Xu , Alan Sullivan

Deep neural networks are typically trained by optimizing a loss function with an SGD variant, in conjunction with a decaying learning rate, until convergence. We show that simple averaging of multiple points along the trajectory of SGD,…

Machine Learning · Computer Science 2019-02-26 Pavel Izmailov , Dmitrii Podoprikhin , Timur Garipov , Dmitry Vetrov , Andrew Gordon Wilson

We consider distributed learning using constant stepsize SGD (DSGD) over several devices, each sending a final model update to a central server. In a final step, the local estimates are aggregated. We prove in the setting of…

Machine Learning · Statistics 2022-10-24 Mike Nguyen , Charly Kirst , Nicole Mücke

We present a unified framework for analyzing local SGD methods in the convex and strongly convex regimes for distributed/federated training of supervised machine learning models. We recover several known methods as a special case of our…

Machine Learning · Computer Science 2020-11-06 Eduard Gorbunov , Filip Hanzely , Peter Richtárik

We study distributed adaptive algorithms with local updates (intermittent communication). Despite the great empirical success of adaptive methods in distributed training of modern machine learning models, the theoretical benefits of local…

Machine Learning · Computer Science 2025-02-13 Ziheng Cheng , Margalit Glasgow

It has been experimentally observed that distributed implementations of mini-batch stochastic gradient descent (SGD) algorithms exhibit speedup saturation and decaying generalization ability beyond a particular batch-size. In this work, we…

Machine Learning · Computer Science 2018-01-09 Dong Yin , Ashwin Pananjady , Max Lam , Dimitris Papailiopoulos , Kannan Ramchandran , Peter Bartlett

Decentralized optimization is emerging as a viable alternative for scalable distributed machine learning, but also introduces new challenges in terms of synchronization costs. To this end, several communication-reduction techniques, such as…

Machine Learning · Computer Science 2022-03-28 Giorgi Nadiradze , Amirmojtaba Sabour , Peter Davies , Shigang Li , Dan Alistarh

Stochastic regularization of neural networks (e.g. dropout) is a wide-spread technique in deep learning that allows for better generalization. Despite its success, continuous-time models, such as neural ordinary differential equation (ODE),…

Machine Learning · Computer Science 2020-06-29 Viktor Oganesyan , Alexandra Volokhova , Dmitry Vetrov

Synchronous mini-batch SGD is state-of-the-art for large-scale distributed machine learning. However, in practice, its convergence is bottlenecked by slow communication rounds between worker nodes. A natural solution to reduce communication…

Machine Learning · Computer Science 2019-04-26 Kumar Kshitij Patel , Aymeric Dieuleveut

Local Stochastic Gradient Descent (SGD) with periodic model averaging (FedAvg) is a foundational algorithm in Federated Learning. The algorithm independently runs SGD on multiple workers and periodically averages the model across all the…

Machine Learning · Computer Science 2022-01-12 Sunwoo Lee , Anit Kumar Sahu , Chaoyang He , Salman Avestimehr

We develop a worst-case complexity theory for stochastically preconditioned stochastic gradient descent (SPSGD) and its accelerated variants under heavy-tailed noise, a setting that encompasses widely used adaptive methods such as Adam,…

Machine Learning · Computer Science 2026-02-17 Yuchen Fang , James Demmel , Javad Lavaei

We study the generalization properties of the popular stochastic optimization method known as stochastic gradient descent (SGD) for optimizing general non-convex loss functions. Our main contribution is providing upper bounds on the…

Machine Learning · Computer Science 2021-08-17 Gergely Neu , Gintare Karolina Dziugaite , Mahdi Haghifam , Daniel M. Roy

This paper studies the generalization performance of iterates obtained by Gradient Descent (GD), Stochastic Gradient Descent (SGD) and their proximal variants in high-dimensional robust regression problems. The number of features is…

Statistics Theory · Mathematics 2024-11-05 Kai Tan , Pierre C. Bellec

Most modern learning problems are highly overparameterized, meaning that there are many more parameters than the number of training data points, and as a result, the training loss may have infinitely many global minima (parameter vectors…

Machine Learning · Computer Science 2019-06-11 Navid Azizan , Sahin Lale , Babak Hassibi

The growth of large language models (LLMs) increases challenges of accelerating distributed training across multiple GPUs in different data centers. Moreover, concerns about data privacy and data exhaustion have heightened interest in…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-18 Zhenheng Tang , Zichen Tang , Junlin Huang , Xinglin Pan , Rudan Yan , Yuxin Wang , Amelie Chi Zhou , Shaohuai Shi , Xiaowen Chu , Bo Li

When using stochastic gradient descent to solve large-scale machine learning problems, a common practice of data processing is to shuffle the training data, partition the data across multiple machines if needed, and then perform several…

Machine Learning · Statistics 2017-10-02 Qi Meng , Wei Chen , Yue Wang , Zhi-Ming Ma , Tie-Yan Liu