中文
相关论文

相关论文: Gradient Descent with Projection Finds Over-Parame…

200 篇论文

It has been shown that gradient descent can yield the zero training loss in the over-parametrized regime (the width of the neural networks is much larger than the number of data points). In this work, combining the ideas of some existing…

最优化与控制 · 数学 2019-11-05 Lei Li

Recent works have empirically analyzed in-context learning and shown that transformers trained on synthetic linear regression tasks can learn to implement ridge regression, which is the Bayes-optimal predictor, given sufficient capacity…

机器学习 · 计算机科学 2023-07-10 Arvind Mahankali , Tatsunori B. Hashimoto , Tengyu Ma

Empirical studies show that gradient-based methods can learn deep neural networks (DNNs) with very good generalization performance in the over-parameterization regime, where DNNs can easily fit a random labeling of the training data. Very…

机器学习 · 计算机科学 2019-11-28 Yuan Cao , Quanquan Gu

We analyze the sample complexity of full-batch Gradient Descent (GD) in the setup of non-smooth Stochastic Convex Optimization. We show that the generalization error of GD, with common choice of hyper-parameters, can be $\tilde \Theta(d/m +…

机器学习 · 计算机科学 2024-04-12 Roi Livni

We study nonparametric regression using an over-parameterized two-layer neural networks trained with algorithmic guarantees in this paper. We consider the setting where the training features are drawn uniformly from the unit sphere in…

机器学习 · 统计学 2025-10-07 Yingzhen Yang , Ping Li

Recent theoretical work has guaranteed that overparameterized networks trained by gradient descent achieve arbitrarily low training error, and sometimes even low test error. The required width, however, is always polynomial in at least one…

机器学习 · 计算机科学 2020-02-18 Ziwei Ji , Matus Telgarsky

Gradient descent finds a global minimum in training deep neural networks despite the objective function being non-convex. The current paper proves gradient descent achieves zero training loss in polynomial time for a deep over-parameterized…

机器学习 · 计算机科学 2019-05-30 Simon S. Du , Jason D. Lee , Haochuan Li , Liwei Wang , Xiyu Zhai

The success of neural networks over the past decade has established them as effective models for many relevant data generating processes. Statistical theory on neural networks indicates graceful scaling of sample complexity. For example,…

机器学习 · 计算机科学 2023-03-28 Yifan Zhu , Hong Jun Jeon , Benjamin Van Roy

It is well understood that neural networks with carefully hand-picked weights provide powerful function approximation and that they can be successfully trained in over-parametrized regimes. Since over-parametrization ensures zero training…

机器学习 · 计算机科学 2024-05-21 G. Welper

The problem of least squares regression of a $d$-dimensional unknown parameter is considered. A stochastic gradient descent based algorithm with weighted iterate-averaging that uses a single pass over the data is studied and its convergence…

信息论 · 计算机科学 2016-06-10 Kobi Cohen , Angelia Nedic , R. Srikant

We demonstrate that applying an eventual decay to the learning rate (LR) in empirical risk minimization (ERM), where the mean-squared-error loss is minimized using standard gradient descent (GD) for training a two-layer neural network with…

机器学习 · 统计学 2026-02-10 Kyle Sung , Kholood Khalil , Noah Forman , Steven Samu , Anastasis Kratsios

We explore the ability of overparameterized shallow neural networks to learn Lipschitz regression functions with and without label noise when trained by Gradient Descent (GD). To avoid the problem that in the presence of noisy labels,…

机器学习 · 计算机科学 2023-01-02 Ilja Kuzborskij , Csaba Szepesvári

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

Multi-layer neural networks are among the most powerful models in machine learning, yet the fundamental reasons for this success defy mathematical understanding. Learning a neural network requires to optimize a non-convex high-dimensional…

机器学习 · 统计学 2022-06-08 Song Mei , Andrea Montanari , Phan-Minh Nguyen

Finding parameters in a deep neural network (NN) that fit training data is a nonconvex optimization problem, but a basic first-order optimization method (gradient descent) finds a global optimizer with perfect fit (zero-loss) in many…

机器学习 · 计算机科学 2025-03-07 Zhiyan Ding , Shi Chen , Qin Li , Stephen Wright

A recent line of research on deep learning focuses on the extremely over-parameterized setting, and shows that when the network width is larger than a high degree polynomial of the training sample size $n$ and the inverse of the target…

机器学习 · 计算机科学 2022-01-03 Zixiang Chen , Yuan Cao , Difan Zou , Quanquan Gu

First-order methods such as stochastic gradient descent (SGD) are currently the standard algorithm for training deep neural networks. Second-order methods, despite their better convergence rate, are rarely used in practice due to the…

机器学习 · 计算机科学 2019-09-26 Tianle Cai , Ruiqi Gao , Jikai Hou , Siyu Chen , Dong Wang , Di He , Zhihua Zhang , Liwei Wang

Deep learning empirically achieves high performance in many applications, but its training dynamics has not been fully understood theoretically. In this paper, we explore theoretical analysis on training two-layer ReLU neural networks in a…

机器学习 · 统计学 2021-06-30 Shunta Akiyama , Taiji Suzuki

We consider the dynamic of gradient descent for learning a two-layer neural network. We assume the input $x\in\mathbb{R}^d$ is drawn from a Gaussian distribution and the label of $x$ satisfies $f^{\star}(x) = a^{\top}|W^{\star}x|$, where…

机器学习 · 计算机科学 2020-07-10 Yuanzhi Li , Tengyu Ma , Hongyang R. Zhang

When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error. In such cases, the choice of the optimization algorithm and its respective hyper-parameters introduces…

机器学习 · 计算机科学 2019-12-06 Gauthier Gidel , Francis Bach , Simon Lacoste-Julien