中文
相关论文

相关论文: SGD with AdaGrad Stepsizes: Full Adaptivity with H…

200 篇论文

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…

Stochastic gradient descent is the method of choice for large scale optimization of machine learning objective functions. Yet, its performance is greatly variable and heavily depends on the choice of the stepsizes. This has motivated a…

机器学习 · 统计学 2019-02-28 Xiaoyu Li , Francesco Orabona

We study adaptive methods for differentially private convex optimization, proposing and analyzing differentially private variants of a Stochastic Gradient Descent (SGD) algorithm with adaptive stepsizes, as well as the AdaGrad algorithm. We…

机器学习 · 计算机科学 2021-06-28 Hilal Asi , John Duchi , Alireza Fallah , Omid Javidbakht , Kunal Talwar

We present adaptive gradient methods (both basic and accelerated) for solving convex composite optimization problems in which the main part is approximately smooth (a.k.a. $(\delta, L)$-smooth) and can be accessed only via a (potentially…

最优化与控制 · 数学 2024-06-11 Anton Rodomanov , Xiaowen Jiang , Sebastian Stich

Adaptive gradient methods, such as AdaGrad, are among the most successful optimization algorithms for neural network training. While these methods are known to achieve better dimensional dependence than stochastic gradient descent (SGD) for…

最优化与控制 · 数学 2025-06-09 Ruichen Jiang , Devyani Maladkar , Aryan Mokhtari

Vanilla gradient methods are often highly sensitive to the choice of stepsize, which typically requires manual tuning. Adaptive methods alleviate this issue and have therefore become widely used. Among them, AdaGrad has been particularly…

机器学习 · 统计学 2026-02-16 Matia Bojovic , Saverio Salzo , Massimiliano Pontil

In this work, we describe a generic approach to show convergence with high probability for both stochastic convex and non-convex optimization with sub-Gaussian noise. In previous works for convex optimization, either the convergence is only…

最优化与控制 · 数学 2023-03-01 Zijian Liu , Ta Duy Nguyen , Thien Hang Nguyen , Alina Ene , Huy Lê Nguyen

Adaptive gradient methods such as AdaGrad and its variants update the stepsize in stochastic gradient descent on the fly according to the gradients received along the way; such methods have gained widespread use in large-scale optimization…

机器学习 · 统计学 2021-04-20 Rachel Ward , Xiaoxia Wu , Leon Bottou

This paper presents a novel adaptation of the Stochastic Gradient Descent (SGD), termed AdaBatchGrad. This modification seamlessly integrates an adaptive step size with an adjustable batch size. An increase in batch size and a decrease in…

We introduce a new adaptive step-size strategy for convex optimization with stochastic gradient that exploits the local geometry of the objective function only by means of a first-order stochastic oracle and without any hyper-parameter…

机器学习 · 计算机科学 2025-09-19 Jean-François Aujol , Jérémie Bigot , Camille Castera

This paper proposes a novel approach to adaptive step sizes in stochastic gradient descent (SGD) by utilizing quantities that we have identified as numerically traceable -- the Lipschitz constant for gradients and a concept of the local…

最优化与控制 · 数学 2024-09-19 Frederik Köhne , Leonie Kreis , Anton Schiela , Roland Herzog

Although stochastic gradient descent (SGD) method and its variants (e.g., stochastic momentum methods, AdaGrad) are the choice of algorithms for solving non-convex problems (especially deep learning), there still remain big gaps between the…

最优化与控制 · 数学 2019-03-07 Zaiyi Chen , Zhuoning Yuan , Jinfeng Yi , Bowen Zhou , Enhong Chen , Tianbao Yang

Stochastic Gradient Descent (SGD) is one of the many iterative optimization methods that are widely used in solving machine learning problems. These methods display valuable properties and attract researchers and industrial machine learning…

机器学习 · 计算机科学 2023-10-04 Farshed Abdukhakimov , Chulu Xiang , Dmitry Kamzolov , Martin Takáč

In this paper we propose several adaptive gradient methods for stochastic optimization. Unlike AdaGrad-type of methods, our algorithms are based on Armijo-type line search and they simultaneously adapt to the unknown Lipschitz constant of…

Recently, Stochastic Gradient Descent (SGD) and its variants have become the dominant methods in the large-scale optimization of machine learning (ML) problems. A variety of strategies have been proposed for tuning the step sizes, ranging…

机器学习 · 计算机科学 2022-08-02 Xiaoyu Li

Selecting an effective step-size is a fundamental challenge in first-order optimization, especially for problems with non-Euclidean geometries. This paper presents a novel adaptive step-size strategy for optimization algorithms that rely on…

最优化与控制 · 数学 2025-10-14 Abbas Khademi , Antonio Silveti-Falls

In this paper, we propose a new, simplified high probability analysis of AdaGrad for smooth, non-convex problems. More specifically, we focus on a particular accelerated gradient (AGD) template (Lan, 2020), through which we recover the…

最优化与控制 · 数学 2022-04-07 Ali Kavis , Kfir Yehuda Levy , Volkan Cevher

Stochastic Gradient Decent (SGD) is one of the core techniques behind the success of deep neural networks. The gradient provides information on the direction in which a function has the steepest rate of change. The main problem with basic…

In this paper, we revisit stochastic gradient descent (SGD) with AdaGrad-type preconditioning. Our contributions are twofold. First, we develop a unified convergence analysis of SGD with adaptive preconditioning under anisotropic or matrix…

机器学习 · 计算机科学 2025-07-01 Dmitry Kovalev

In stochastic optimization, a common tool to deal sequentially with large sample is to consider the well-known stochastic gradient algorithm. Nevertheless, since the stepsequence is the same for each direction, this can lead to bad results…

最优化与控制 · 数学 2023-03-03 Antoine Godichon-Baggioni , Pierre Tarrago
‹ 上一页 1 2 3 10 下一页 ›