中文
相关论文

相关论文: Towards Theoretical Understanding of Large Batch T…

200 篇论文

When using large-batch training to speed up stochastic gradient descent, learning rates must adapt to new batch sizes in order to maximize speed-ups and preserve model quality. Re-tuning learning rates is resource intensive, while fixed…

机器学习 · 计算机科学 2020-07-13 Tyler B. Johnson , Pulkit Agrawal , Haijie Gu , Carlos Guestrin

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

We show that parametric models trained by a stochastic gradient method (SGM) with few iterations have vanishing generalization error. We prove our results by arguing that SGM is algorithmically stable in the sense of Bousquet and Elisseeff.…

机器学习 · 计算机科学 2016-02-09 Moritz Hardt , Benjamin Recht , Yoram Singer

Stochastic optimization algorithms with variance reduction have proven successful for minimizing large finite sums of functions. Unfortunately, these techniques are unable to deal with stochastic perturbations of input data, induced for…

机器学习 · 统计学 2017-11-16 Alberto Bietti , Julien Mairal

The main aim of this paper is to provide an analysis of gradient descent (GD) algorithms with gradient errors that do not necessarily vanish, asymptotically. In particular, sufficient conditions are presented for both stability (almost sure…

系统与控制 · 计算机科学 2017-09-19 Arunselvan Ramaswamy , Shalabh Bhatnagar

Stochastic gradient descent (SGD) is a promising method for solving large-scale inverse problems, due to its excellent scalability with respect to data size. The current mathematical theory in the lens of regularization theory predicts that…

最优化与控制 · 数学 2021-08-10 Bangti Jin , Zehui Zhou , Jun Zou

The performance of stochastic gradient descent (SGD), which is the simplest first-order optimizer for training deep neural networks, depends on not only the learning rate but also the batch size. They both affect the number of iterations…

机器学习 · 统计学 2024-02-26 Kento Imaizumi , Hideaki Iiduka

Distributed implementations of mini-batch stochastic gradient descent (SGD) suffer from communication overheads, attributed to the high frequency of gradient updates inherent in small-batch training. Training with large batches can reduce…

机器学习 · 统计学 2018-06-12 Lingjiao Chen , Hongyi Wang , Jinman Zhao , Dimitris Papailiopoulos , Paraschos Koutris

SGD is the widely adopted method to train CNN. Conceptually it approximates the population with a randomly sampled batch; then it evenly trains batches by conducting a gradient update on every batch in an epoch. In this paper, we…

机器学习 · 计算机科学 2017-03-29 Linnan Wang , Yi Yang , Martin Renqiang Min , Srimat Chakradhar

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 analyzes the trajectories of stochastic gradient descent (SGD) to help understand the algorithm's convergence properties in non-convex problems. We first show that the sequence of iterates generated by SGD remains bounded and…

最优化与控制 · 数学 2020-06-22 Panayotis Mertikopoulos , Nadav Hallak , Ali Kavis , Volkan Cevher

Stochastic convex optimization is a basic and well studied primitive in machine learning. It is well known that convex and Lipschitz functions can be minimized efficiently using Stochastic Gradient Descent (SGD). The Normalized Gradient…

机器学习 · 计算机科学 2015-10-29 Elad Hazan , Kfir Y. Levy , Shai Shalev-Shwartz

Momentum Stochastic Gradient Descent (MSGD) algorithm has been widely applied to many nonconvex optimization problems in machine learning, e.g., training deep neural networks, variational Bayesian inference, and etc. Despite its empirical…

机器学习 · 计算机科学 2021-03-09 Tianyi Liu , Zhehui Chen , Enlu Zhou , Tuo Zhao

Commonly used optimization algorithms often show a trade-off between good generalization and fast training times. For instance, stochastic gradient descent (SGD) tends to have good generalization; however, adaptive gradient methods have…

机器学习 · 计算机科学 2023-06-14 Aditya Cowsik , Tankut Can , Paolo Glorioso

We propose a new framework, inspired by random matrix theory, for analyzing the dynamics of stochastic gradient descent (SGD) when both number of samples and dimensions are large. This framework applies to any fixed stepsize and the finite…

最优化与控制 · 数学 2021-02-09 Courtney Paquette , Kiwon Lee , Fabian Pedregosa , Elliot Paquette

This work studies the generalization error of gradient methods. More specifically, we focus on how training steps $T$ and step-size $\eta$ might affect generalization in smooth stochastic convex optimization (SCO) problems. We first provide…

机器学习 · 计算机科学 2023-05-11 Peiyuan Zhang , Jiaye Teng , Jingzhao Zhang

We give a new separation result between the generalization performance of stochastic gradient descent (SGD) and of full-batch gradient descent (GD) in the fundamental stochastic convex optimization model. While for SGD it is well-known that…

机器学习 · 计算机科学 2021-07-01 Idan Amir , Tomer Koren , Roi Livni

In this paper, we provide a theoretical study of noise geometry for minibatch stochastic gradient descent (SGD), a phenomenon where noise aligns favorably with the geometry of local landscape. We propose two metrics, derived from analyzing…

机器学习 · 计算机科学 2024-02-02 Mingze Wang , Lei Wu

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 variance-reduced gradient (SVRG) is a classical optimization method. Although it is theoretically proved to have better convergence performance than stochastic gradient descent (SGD), the generalization performance of SVRG…

机器学习 · 统计学 2019-08-20 Hao Jin , Dachao Lin , Zhihua Zhang