中文
相关论文

相关论文: Last Iterate Risk Bounds of SGD with Decaying Step…

200 篇论文

Minimax optimal convergence rates for classes of stochastic convex optimization problems are well characterized, where the majority of results utilize iterate averaged stochastic gradient descent (SGD) with polynomially decaying step sizes.…

机器学习 · 计算机科学 2019-10-30 Rong Ge , Sham M. Kakade , Rahul Kidambi , Praneeth Netrapalli

There is an increasing realization that algorithmic inductive biases are central in preventing overfitting; empirically, we often see a benign overfitting phenomenon in overparameterized settings for natural learning algorithms, such as…

机器学习 · 计算机科学 2021-10-14 Difan Zou , Jingfeng Wu , Vladimir Braverman , Quanquan Gu , Sham M. Kakade

Stochastic gradient descent (SGD) is one of the most widely used algorithms for large scale optimization problems. While classical theoretical analysis of SGD for convex problems studies (suffix) \emph{averages} of iterates and obtains…

最优化与控制 · 数学 2019-05-30 Prateek Jain , Dheeraj Nagaraj , Praneeth Netrapalli

Accelerated stochastic gradient descent (ASGD) is a workhorse in deep learning and often achieves better generalization performance than SGD. However, existing optimization theory can only explain the faster convergence of ASGD, but cannot…

机器学习 · 计算机科学 2023-11-27 Xuheng Li , Yihe Deng , Jingfeng Wu , Dongruo Zhou , Quanquan Gu

Stochastic Gradient Descent (SGD) is among the simplest and most popular methods in optimization. The convergence rate for SGD has been extensively studied and tight analyses have been established for the running average scheme, but the…

最优化与控制 · 数学 2021-06-29 Daogao Liu , Zhou Lu

Most results on Stochastic Gradient Descent (SGD) in the convex and smooth setting are presented under the form of bounds on the ergodic function value gap. It is an open question whether bounds can be derived directly on the last iterate…

最优化与控制 · 数学 2025-07-21 Guillaume Garrigos , Daniel Cortild , Lucas Ketels , Juan Peypouquet

Stochastic gradient descent (SGD) has achieved great success due to its superior performance in both optimization and generalization. Most of existing generalization analyses are made for single-pass SGD, which is a less practical variant…

机器学习 · 计算机科学 2022-03-08 Difan Zou , Jingfeng Wu , Vladimir Braverman , Quanquan Gu , Sham M. Kakade

We consider the well-studied setting of minimizing a convex Lipschitz function using either gradient descent (GD) or its stochastic variant (SGD), and examine the last iterate convergence. By now, it is known that standard stepsize choices…

最优化与控制 · 数学 2026-04-16 Guy Kornowski , Ohad Shamir

We study population convergence guarantees of stochastic gradient descent (SGD) for smooth convex objectives in the interpolation regime, where the noise at optimum is zero or near zero. The behavior of the last iterate of SGD in this…

机器学习 · 计算机科学 2025-07-29 Amit Attia , Matan Schliserman , Uri Sherman , Tomer Koren

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

Stochastic gradient descent (SGD) is a widely used algorithm in machine learning, particularly for neural network training. Recent studies on SGD for canonical quadratic optimization or linear regression show it attains well generalization…

机器学习 · 计算机科学 2024-09-17 Haihan Zhang , Yuanshi Liu , Qianwen Chen , Cong Fang

Theoretically understanding stochastic gradient descent (SGD) in overparameterized models has led to the development of several optimization algorithms that are widely used in practice today. Recent work by~\citet{zou2021benign} provides…

机器学习 · 计算机科学 2025-06-19 Alexandru Meterez , Depen Morwani , Costin-Andrei Oncescu , Jingfeng Wu , Cengiz Pehlevan , Sham Kakade

In the past several years, the last-iterate convergence of the Stochastic Gradient Descent (SGD) algorithm has triggered people's interest due to its good performance in practice but lack of theoretical understanding. For Lipschitz convex…

机器学习 · 计算机科学 2026-03-20 Zijian Liu , Zhengyuan Zhou

The stochastic gradient descent (SGD) optimization algorithm plays a central role in a series of machine learning applications. The scientific literature provides a vast amount of upper error bounds for the SGD method. Much less attention…

数值分析 · 数学 2020-10-05 Arnulf Jentzen , Philippe von Wurstemberger

Many modern learning tasks involve fitting nonlinear models to data which are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Due to this overparameterization, the training…

机器学习 · 计算机科学 2018-12-27 Samet Oymak , Mahdi Soltanolkotabi

Stochastic Gradient Descent (SGD) plays a central role in modern machine learning. While there is extensive work on providing error upper bound for SGD, not much is known about SGD error lower bound. In this paper, we study the convergence…

最优化与控制 · 数学 2019-10-21 Zhiyan Ding , Yiding Chen , Qin Li , Xiaojin Zhu

Stochastic gradient descent (SGD) is perhaps the most prevalent optimization method in modern machine learning. Contrary to the empirical practice of sampling from the datasets without replacement and with (possible) reshuffling at each…

最优化与控制 · 数学 2024-02-08 Xufeng Cai , Cheuk Yin Lin , Jelena Diakonikolas

Stochastic gradient descent (SGD) algorithm and its variations have been effectively used to optimize neural network models. However, with the rapid growth of big data and deep learning, SGD is no longer the most suitable choice due to its…

机器学习 · 计算机科学 2024-02-13 Anuraganand Sharma

This work characterizes the benefits of averaging schemes widely used in conjunction with stochastic gradient descent (SGD). In particular, this work provides a sharp analysis of: (1) mini-batching, a method of averaging many samples of a…

机器学习 · 统计学 2018-08-01 Prateek Jain , Sham M. Kakade , Rahul Kidambi , Praneeth Netrapalli , Aaron Sidford

We study to what extent may stochastic gradient descent (SGD) be understood as a "conventional" learning rule that achieves generalization performance by obtaining a good fit to training data. We consider the fundamental stochastic convex…

机器学习 · 计算机科学 2023-01-13 Tomer Koren , Roi Livni , Yishay Mansour , Uri Sherman
‹ 上一页 1 2 3 10 下一页 ›