中文
相关论文

相关论文: Revisiting Gradient Clipping: Stochastic bias and …

200 篇论文

Stochastic Gradient Descent (SGD) is a central tool in machine learning. We prove that SGD converges to zero loss, even with a fixed (non-vanishing) learning rate - in the special case of homogeneous linear classifiers with smooth monotone…

机器学习 · 统计学 2022-04-19 Mor Shpigel Nacson , Nathan Srebro , Daniel Soudry

In machine learning, stochastic gradient descent (SGD) is widely deployed to train models using highly non-convex objectives with equally complex noise models. Unfortunately, SGD theory often makes restrictive assumptions that fail to…

机器学习 · 计算机科学 2022-10-11 Vivak Patel , Shushu Zhang , Bowen Tian

SGD (Stochastic Gradient Descent) is a popular algorithm for large scale optimization problems due to its low iterative cost. However, SGD can not achieve linear convergence rate as FGD (Full Gradient Descent) because of the inherent…

机器学习 · 计算机科学 2017-12-05 Aixiang Chen , Bingchuan Chen , Xiaolong Chai , Rui Bian , Hengguang Li

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…

最优化与控制 · 数学 2021-04-02 Vivak Patel , Shushu Zhang

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

In this paper, the problem of distributed optimization is studied via a network of agents. Each agent only has access to a noisy gradient of its own objective function, and can communicate with its neighbors via a network. To handle this…

最优化与控制 · 数学 2025-06-19 Yuchen Yang , Kaihong Lu , Long Wang

Stochastic Gradient Descent (SGD) is the workhorse algorithm of deep learning technology. At each step of the training phase, a mini batch of samples is drawn from the training dataset and the weights of the neural network are adjusted…

无序系统与神经网络 · 物理学 2022-09-07 Francesca Mignacco , Pierfrancesco Urbani

The stability and generalization of stochastic gradient-based methods provide valuable insights into understanding the algorithmic performance of machine learning models. As the main workhorse for deep learning, stochastic gradient descent…

机器学习 · 统计学 2021-02-24 Tao Sun , Dongsheng Li , Bao Wang

The success of deep learning has led to a rising interest in the generalization property of the stochastic gradient descent (SGD) method, and stability is one popular approach to study it. Existing works based on stability have studied…

机器学习 · 统计学 2019-03-08 Yi Zhou , Yingbin Liang , Huishuai Zhang

This paper presents a novel stochastic gradient descent algorithm for constrained optimization. The proposed algorithm randomly samples constraints and components of the finite sum objective function and relies on a relaxed logarithmic…

最优化与控制 · 数学 2025-05-13 Naum Dimitrieski , Jing Cao , Christian Ebenbauer

Deep neural networks (DNN) are typically optimized using stochastic gradient descent (SGD). However, the estimation of the gradient using stochastic samples tends to be noisy and unreliable, resulting in large gradient variance and bad…

机器学习 · 计算机科学 2021-05-18 Xingyi Yang

Stochastic gradient descent (SGD) is the workhorse of large-scale learning, yet classical analyses rely on assumptions that can be either too strong (bounded variance) or too coarse (uniform noise). The expected smoothness (ES) condition…

机器学习 · 计算机科学 2025-10-28 Yuta Kawamoto , Hideaki Iiduka

Stochastic gradient descent (SGD) is widely believed to perform implicit regularization when used to train deep neural networks, but the precise manner in which this occurs has thus far been elusive. We prove that SGD minimizes an average…

机器学习 · 计算机科学 2018-01-17 Pratik Chaudhari , Stefano Soatto

When implementing the gradient descent method in low precision, the employment of stochastic rounding schemes helps to prevent stagnation of convergence caused by the vanishing gradient effect. Unbiased stochastic rounding yields zero bias…

机器学习 · 计算机科学 2023-02-28 Lu Xia , Stefano Massei , Michiel E. Hochstenbach , Barry Koren

We provide a new understanding of the stochastic gradient bandit algorithm by showing that it converges to a globally optimal policy almost surely using \emph{any} constant learning rate. This result demonstrates that the stochastic…

机器学习 · 计算机科学 2025-02-12 Jincheng Mei , Bo Dai , Alekh Agarwal , Sharan Vaswani , Anant Raj , Csaba Szepesvari , Dale Schuurmans

We analyze the variance of stochastic gradients along negative curvature directions in certain non-convex machine learning models and show that stochastic gradients exhibit a strong component along these directions. Furthermore, we show…

机器学习 · 计算机科学 2018-09-18 Hadi Daneshmand , Jonas Kohler , Aurelien Lucchi , Thomas Hofmann

A vast literature on convergence guarantees for gradient descent and derived methods exists at the moment. However, a simple practical situation remains unexplored: when a fixed step size is used, can we expect gradient descent to converge…

机器学习 · 计算机科学 2024-12-10 Alexandru Crăciun , Debarghya Ghoshdastidar

The injection of heavy-tailed noise into the iterates of stochastic gradient descent (SGD) has garnered growing interest in recent years due to its theoretical and empirical benefits for optimization and generalization. However, its…

机器学习 · 统计学 2025-05-13 Umut Şimşekli , Mert Gürbüzbalaban , Sinan Yıldırım , Lingjiong Zhu

Recent years have seen increased interest in performance guarantees of gradient descent algorithms for non-convex optimization. A number of works have uncovered that gradient noise plays a critical role in the ability of gradient descent…

最优化与控制 · 数学 2019-08-21 Stefan Vlaski , Ali H. Sayed

Stochastic first-order methods such as Stochastic Extragradient (SEG) or Stochastic Gradient Descent-Ascent (SGDA) for solving smooth minimax problems and, more generally, variational inequality problems (VIP) have been gaining a lot of…