中文
相关论文

相关论文: Tighter Theory for Local SGD on Identical and Hete…

200 篇论文

LocalSGD and SCAFFOLD are widely used methods in distributed stochastic optimization, with numerous applications in machine learning, large-scale data processing, and federated learning. However, rigorously establishing their theoretical…

最优化与控制 · 数学 2025-02-25 Ruichen Luo , Sebastian U Stich , Samuel Horváth , Martin Takáč

To accelerate the training of machine learning models, distributed stochastic gradient descent (SGD) and its variants have been widely adopted, which apply multiple workers in parallel to speed up training. Among them, Local SGD has gained…

机器学习 · 计算机科学 2020-01-01 Xianfeng Liang , Shuheng Shen , Jingchang Liu , Zhen Pan , Enhong Chen , Yifei Cheng

Stochastic Gradient Descent (SGD) is a workhorse in machine learning, yet its slow convergence can be a computational bottleneck. Variance reduction techniques such as SAG, SVRG and SAGA have been proposed to overcome this weakness,…

机器学习 · 计算机科学 2016-02-29 Thomas Hofmann , Aurelien Lucchi , Simon Lacoste-Julien , Brian McWilliams

Artificial intelligence has advanced rapidly through large neural networks trained on massive datasets using thousands of GPUs or TPUs. Such training can occupy entire data centers for weeks and requires enormous computational and energy…

最优化与控制 · 数学 2026-01-07 Artavazd Maranjyan

We provide an improved analysis of standard differentially private gradient descent for linear regression under the squared error loss. Under modest assumptions on the input, we characterize the distribution of the iterate at each time…

机器学习 · 计算机科学 2024-02-22 Gavin Brown , Krishnamurthy Dvijotham , Georgina Evans , Daogao Liu , Adam Smith , Abhradeep Thakurta

Accurate estimation of Intrinsic Dimensionality (ID) is of crucial importance in many data mining and machine learning tasks, including dimensionality reduction, outlier detection, similarity search and subspace clustering. However, since…

Stochastic optimization via Stochastic Gradient Descent (SGD) is a fundamental problem in statistics and optimization. This paper revisits Stochastic Gradient Descent (SGD) for strongly convex objectives, establishing tight, uniform-in-time…

最优化与控制 · 数学 2026-03-19 Kang Chen , Yasong Feng , Tianyu Wang

Modern machine learning architectures are often highly expressive. They are usually over-parameterized and can interpolate the data by driving the empirical loss close to zero. We analyze the convergence of Local SGD (or FedAvg) for such…

机器学习 · 计算机科学 2024-06-11 Tiancheng Qin , S. Rasoul Etesami , César A. Uribe

We consider the optimization problem of minimizing the logistic loss with gradient descent to train a linear model for binary classification with separable data. With a budget of $T$ iterations, it was recently shown that an accelerated…

机器学习 · 计算机科学 2026-02-16 Michael Crawshaw , Mingrui Liu

Stochastic Gradient Descent (SGD) is one of the simplest and most popular stochastic optimization methods. While it has already been theoretically studied for decades, the classical analysis usually required non-trivial smoothness…

机器学习 · 计算机科学 2013-01-01 Ohad Shamir , Tong Zhang

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…

机器学习 · 统计学 2022-10-24 Mike Nguyen , Charly Kirst , Nicole Mücke

We study problem-dependent rates, i.e., generalization errors that scale near-optimally with the variance, the effective loss, or the gradient norms evaluated at the "best hypothesis." We introduce a principled framework dubbed "uniform…

机器学习 · 统计学 2020-12-25 Yunbei Xu , Assaf Zeevi

Statistical heterogeneity is a measure of how skewed the samples of a dataset are. It is a common problem in the study of differential privacy that the usage of a statistically heterogeneous dataset results in a significant loss of…

机器学习 · 计算机科学 2024-12-02 Mary Scott , Graham Cormode , Carsten Maple

We study a distributed consensus-based stochastic gradient descent (SGD) algorithm and show that the rate of convergence involves the spectral properties of two matrices: the standard spectral gap of a weight matrix from the network…

最优化与控制 · 数学 2016-09-02 Avleen S. Bijral , Anand D. Sarwate , Nathan Srebro

In this dissertation we propose alternative analysis of distributed stochastic gradient descent (SGD) algorithms that rely on spectral properties of the data covariance. As a consequence we can relate questions pertaining to speedups and…

最优化与控制 · 数学 2016-09-03 Avleen S. Bijral

We consider stochastic gradient descent (SGD) for least-squares regression with potentially several passes over the data. While several passes have been widely reported to perform practically better in terms of predictive performance on…

机器学习 · 计算机科学 2018-11-26 Loucas Pillaud-Vivien , Alessandro Rudi , Francis Bach

Empirical studies using Regression Discontinuity (RD) designs often explore heterogeneous treatment effects based on pretreatment covariates, even though no formal statistical methods exist for such analyses. This has led to the widespread…

计量经济学 · 经济学 2025-07-08 Sebastian Calonico , Matias D. Cattaneo , Max H. Farrell , Filippo Palomba , Rocio Titiunik

Recently, local SGD has got much attention and been extensively studied in the distributed learning community to overcome the communication bottleneck problem. However, the superiority of local SGD to minibatch SGD only holds in quite…

机器学习 · 计算机科学 2021-06-15 Tomoya Murata , Taiji Suzuki

We study the multifractal analysis of self-similar measures arising from random homogeneous iterated function systems. Under the assumption of the uniform strong separation condition, we see that this analysis parallels that of the…

动力系统 · 数学 2019-12-23 Kathryn E. Hare , Kevin G. Hare , Sascha Troscheit

While powerful methods have been developed for high-dimensional hypothesis testing assuming orthogonal parameters, current approaches struggle to generalize to the more common non-orthogonal case. We propose Stable Distillation (SD), a…

统计方法学 · 统计学 2025-01-10 Ryan Christ , Ira Hall , David Steinsaltz