中文
相关论文

相关论文: Revisiting Normalized Gradient Descent: Fast Evasi…

200 篇论文

We consider the problem of approximating a function by an element of a nonlinear manifold which admits a differentiable parametrization, typical examples being neural networks with differentiable activation functions or tensor networks.…

机器学习 · 计算机科学 2026-04-20 Anthony Nouy , Agustín Somacal

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 gradient descent (SGD) is widely used in machine learning. Although being commonly viewed as a fast but not accurate version of gradient descent (GD), it always finds better solutions than GD for modern neural networks. In order…

机器学习 · 计算机科学 2018-08-17 Robert Kleinberg , Yuanzhi Li , Yang Yuan

A central challenge to many fields of science and engineering involves minimizing non-convex error functions over continuous, high dimensional spaces. Gradient descent or quasi-Newton methods are almost ubiquitously used to perform such…

机器学习 · 计算机科学 2014-05-29 Razvan Pascanu , Yann N. Dauphin , Surya Ganguli , Yoshua Bengio

Stochastic gradient descent (SGD) with stochastic momentum is popular in nonconvex stochastic optimization and particularly for the training of deep neural networks. In standard SGD, parameters are updated by improving along the path of the…

机器学习 · 计算机科学 2021-06-08 Jun-Kun Wang , Chi-Heng Lin , Jacob Abernethy

We propose efficient numerical schemes for implementing the natural gradient descent (NGD) for a broad range of metric spaces with applications to PDE-based optimization problems. Our technique represents the natural gradient direction as a…

最优化与控制 · 数学 2023-01-12 Levon Nurbekyan , Wanzhou Lei , Yunan Yang

This work shows that applying Gradient Descent (GD) with a fixed step size to minimize a (possibly nonconvex) quadratic function is equivalent to running the Power Method (PM) on the gradients. The connection between GD with a fixed step…

最优化与控制 · 数学 2022-11-03 Rachael Tappenden , Martin Takáč

In this paper, we provide some analysis on the asymptotic escape of strict saddles in manifold optimization using the projected gradient descent (PGD) algorithm. One of our main contributions is that we extend the current analysis to…

最优化与控制 · 数学 2020-06-30 Thomas Y. Hou , Zhenzhen Li , Ziyun Zhang

In this work, we analyze the global convergence property of coordinate gradient descent with random choice of coordinates and stepsizes for non-convex optimization problems. Under generic assumptions, we prove that the algorithm iterate…

最优化与控制 · 数学 2022-12-01 Ziang Chen , Yingzhou Li , Jianfeng Lu

In this paper, we examine the time it takes for stochastic gradient descent (SGD) to reach the global minimum of a general, non-convex loss function. We approach this question through the lens of randomly perturbed dynamical systems and…

最优化与控制 · 数学 2025-06-10 Waïss Azizian , Franck Iutzeler , Jérôme Malick , Panayotis Mertikopoulos

We analyze stochastic gradient descent for optimizing non-convex functions. In many cases for non-convex functions the goal is to find a reasonable local minimum, and the main concern is that gradient updates are trapped in saddle points.…

机器学习 · 计算机科学 2015-03-10 Rong Ge , Furong Huang , Chi Jin , Yang Yuan

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 standard optimization method to minimize a training error with respect to network parameters in modern neural network learning. However, it typically suffers from proliferation of saddle points in the…

机器学习 · 计算机科学 2017-11-23 Haiping Huang , Taro Toyoizumi

This paper considers the problem of understanding the exit time for trajectories of gradient-related first-order methods from saddle neighborhoods under some initial boundary conditions. Given the 'flat' geometry around saddle points,…

最优化与控制 · 数学 2023-10-10 Rishabh Dixit , Mert Gurbuzbalaban , Waheed U. Bajwa

A central challenge to many fields of science and engineering involves minimizing non-convex error functions over continuous, high dimensional spaces. Gradient descent or quasi-Newton methods are almost ubiquitously used to perform such…

机器学习 · 计算机科学 2014-06-11 Yann Dauphin , Razvan Pascanu , Caglar Gulcehre , Kyunghyun Cho , Surya Ganguli , Yoshua Bengio

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

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

High-dimensional non-convex optimization problems in engineering design, control, and learning are often hindered by saddle points, flat plateaus, and strongly anisotropic curvature. This paper develops a unified, curvature-adaptive…

最优化与控制 · 数学 2025-09-04 Ronald Katende , Henry Kasumba

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

This paper considers the problem of understanding the behavior of a general class of accelerated gradient methods on smooth nonconvex functions. Motivated by some recent works that have proposed effective algorithms, based on Polyak's heavy…

最优化与控制 · 数学 2026-04-07 Rishabh Dixit , Mert Gurbuzbalaban , Waheed U. Bajwa