中文
相关论文

相关论文: Non-asymptotic Analysis of Biased Adaptive Stochas…

200 篇论文

Stochastic gradient descent (SGD) and its variants are the main workhorses for solving large-scale optimization problems with nonconvex objective functions. Although the convergence of SGDs in the (strongly) convex case is well-understood,…

机器学习 · 计算机科学 2023-10-20 Aritra Dutta , El Houcine Bergou , Soumia Boucherouite , Nicklas Werge , Melih Kandemir , Xin Li

Stochastic gradient descent (SGD) has taken the stage as the primary workhorse for large-scale machine learning. It is often used with its adaptive variants such as AdaGrad, Adam, and AMSGrad. This paper proposes an adaptive stochastic…

机器学习 · 计算机科学 2021-01-01 Tianyi Chen , Ziye Guo , Yuejiao Sun , Wotao Yin

We consider a variant of the stochastic gradient descent (SGD) with a random learning rate and reveal its convergence properties. SGD is a widely used stochastic optimization algorithm in machine learning, especially deep learning. Numerous…

机器学习 · 统计学 2025-09-09 Naoki Yoshida , Shogo Nakakita , Masaaki Imaizumi

Stochastic Gradient Descent (SGD) has played a central role in machine learning. However, it requires a carefully hand-picked stepsize for fast convergence, which is notoriously tedious and time-consuming to tune. Over the last several…

机器学习 · 计算机科学 2019-06-10 Zhenxun Zhuang , Ashok Cutkosky , Francesco Orabona

Adaptive Moment Estimation (Adam), which combines Adaptive Learning Rate and Momentum, would be the most popular stochastic optimizer for accelerating the training of deep neural networks. However, it is empirically known that Adam often…

机器学习 · 计算机科学 2022-06-15 Zeke Xie , Xinrui Wang , Huishuai Zhang , Issei Sato , Masashi Sugiyama

We study the generalization error of randomized learning algorithms -- focusing on stochastic gradient descent (SGD) -- using a novel combination of PAC-Bayes and algorithmic stability. Importantly, our generalization bounds hold for all…

机器学习 · 计算机科学 2020-06-23 Ben London

In this paper, we consider a general stochastic optimization problem which is often at the core of supervised learning, such as deep learning and linear classification. We consider a standard stochastic gradient descent (SGD) method with a…

机器学习 · 统计学 2018-12-27 Lam M. Nguyen , Nam H. Nguyen , Dzung T. Phan , Jayant R. Kalagnanam , Katya Scheinberg

This article introduces a novel family of optimization algorithms - Anisotropic Gaussian Smoothing Gradient Descent (AGS-GD), AGS-Stochastic Gradient Descent (AGS-SGD), and AGS-Adam - that employ anisotropic Gaussian smoothing to enhance…

最优化与控制 · 数学 2024-11-19 Andrew Starnes , Guannan Zhang , Viktor Reshniak , Clayton Webster

Stochastic gradient algorithms are the main focus of large-scale optimization problems and led to important successes in the recent advancement of the deep learning algorithms. The convergence of SGD depends on the careful choice of…

机器学习 · 计算机科学 2017-03-03 Caglar Gulcehre , Jose Sotelo , Marcin Moczulski , Yoshua Bengio

Iterative procedures for parameter estimation based on stochastic gradient descent allow the estimation to scale to massive data sets. However, in both theory and practice, they suffer from numerical instability. Moreover, they are…

统计方法学 · 统计学 2016-06-08 Panos Toulis , Dustin Tran , Edoardo M. Airoldi

We study finite-sum nonconvex optimization problems, where the objective function is an average of $n$ nonconvex functions. We propose a new stochastic gradient descent algorithm based on nested variance reduction. Compared with…

机器学习 · 计算机科学 2020-10-20 Dongruo Zhou , Pan Xu , Quanquan Gu

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

In this paper, we proposed a new technique, {\em variance controlled stochastic gradient} (VCSG), to improve the performance of the stochastic variance reduced gradient (SVRG) algorithm. To avoid over-reducing the variance of gradient by…

机器学习 · 计算机科学 2021-02-22 Jia Bi , Steve R. Gunn

Large-scale nonconvex optimization problems are ubiquitous in modern machine learning, and among practitioners interested in solving them, Stochastic Gradient Descent (SGD) reigns supreme. We revisit the analysis of SGD in the nonconvex…

最优化与控制 · 数学 2020-07-27 Ahmed Khaled , Peter Richtárik

Stochastic gradient descent (SGD) is a simple and popular method to solve stochastic optimization problems which arise in machine learning. For strongly convex problems, its convergence rate was known to be O(\log(T)/T), by running SGD for…

机器学习 · 计算机科学 2015-03-19 Alexander Rakhlin , Ohad Shamir , Karthik Sridharan

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

Conditional stochastic optimization covers a variety of applications ranging from invariant learning and causal inference to meta-learning. However, constructing unbiased gradient estimators for such problems is challenging due to the…

最优化与控制 · 数学 2024-06-04 Yifan Hu , Siqi Zhang , Xin Chen , Niao He

Traditional analyses in non-convex optimization typically rely on the smoothness assumption, namely requiring the gradients to be Lipschitz. However, recent evidence shows that this smoothness condition does not capture the properties of…

机器学习 · 计算机科学 2022-08-25 Michael Crawshaw , Mingrui Liu , Francesco Orabona , Wei Zhang , Zhenxun Zhuang

We study stochastic algorithms for solving nonconvex optimization problems with a convex yet possibly nonsmooth regularizer, which find wide applications in many practical machine learning applications. However, compared to asynchronous…

机器学习 · 计算机科学 2018-09-18 Rui Zhu , Di Niu , Zongpeng Li

Stochastic gradient descent (SGD) optimization methods are nowadays the method of choice for the training of deep neural networks (DNNs) in artificial intelligence systems. In practically relevant training problems, usually not the plain…

最优化与控制 · 数学 2024-08-01 Steffen Dereich , Arnulf Jentzen