English
Related papers

Related papers: Gradient Descent Finds Over-Parameterized Neural N…

200 papers

Stochastic gradient descent algorithms for training linear and kernel predictors are gaining more and more importance, thanks to their scalability. While various methods have been proposed to speed up their convergence, the model selection…

Machine Learning · Computer Science 2014-06-17 Francesco Orabona

In a series of recent theoretical works, it was shown that strongly over-parameterized neural networks trained with gradient-based methods could converge exponentially fast to zero training loss, with their parameters hardly varying. In…

Optimization and Control · Mathematics 2020-01-08 Lenaic Chizat , Edouard Oyallon , Francis Bach

Natural gradient descent (NGD) is a powerful optimization technique for machine learning, but the computational complexity of the inverse Fisher information matrix limits its application in training deep neural networks. To overcome this…

Machine Learning · Computer Science 2024-12-11 Weihua Liu , Said Boumaraf , Jianwu Li , Chaochao Lin , Xiabi Liu , Lijuan Niu , Naoufel Werghi

Recent work has shown that training wide neural networks with gradient descent is formally equivalent to computing the mean of the posterior distribution in a Gaussian Process (GP) with the Neural Tangent Kernel (NTK) as the prior…

Machine Learning · Computer Science 2024-09-11 Sergio Calvo-Ordoñez , Konstantina Palla , Kamil Ciosek

We introduce the neural tangent kernel (NTK) regime for two-layer neural operators and analyze their generalization properties. For early-stopped gradient descent (GD), we derive fast convergence rates that are known to be minimax optimal…

Machine Learning · Statistics 2024-12-24 Mike Nguyen , Nicole Mücke

We investigate the generalization and optimization properties of shallow neural-network classifiers trained by gradient descent in the interpolating regime. Specifically, in a realizable scenario where model weights can achieve arbitrarily…

Machine Learning · Statistics 2023-03-29 Hossein Taheri , Christos Thrampoulidis

Recent works have examined theoretical and empirical properties of wide neural networks trained in the Neural Tangent Kernel (NTK) regime. Given that biological neural networks are much wider than their artificial counterparts, we consider…

Machine Learning · Computer Science 2022-07-14 Akhilan Boopathy , Ila Fiete

Over-parametrization is an important technique in training neural networks. In both theory and practice, training a larger network allows the optimization algorithm to avoid bad local optimal solutions. In this paper we study a closely…

Machine Learning · Statistics 2020-10-23 Xiang Wang , Chenwei Wu , Jason D. Lee , Tengyu Ma , Rong Ge

Recent results show that estimates defined by over-parametrized deep neural networks learned by applying gradient descent to a regularized empirical $L_2$ risk are universally consistent and achieve good rates of convergence. In this paper,…

Machine Learning · Statistics 2023-11-27 Selina Drews , Michael Kohler

In suitably initialized wide networks, small learning rates transform deep neural networks (DNNs) into neural tangent kernel (NTK) machines, whose training dynamics is well-approximated by a linear weight expansion of the network at…

Machine Learning · Computer Science 2020-10-29 Stanislav Fort , Gintare Karolina Dziugaite , Mansheej Paul , Sepideh Kharaghani , Daniel M. Roy , Surya Ganguli

Classical statistical learning theory predicts that overparameterized models should exhibit severe overfitting, yet modern deep neural networks with far more parameters than training samples consistently generalize well. This contradiction…

Machine Learning · Computer Science 2026-04-10 Zeran Johannsen

We perform an average case analysis of the generalization dynamics of large neural networks trained using gradient descent. We study the practically-relevant "high-dimensional" regime where the number of free parameters in the network is on…

Machine Learning · Statistics 2017-10-11 Madhu S. Advani , Andrew M. Saxe

We investigate changing the bandwidth of a translational-invariant kernel during training when solving kernel regression with gradient descent. We present a theoretical bound on the out-of-sample generalization error that advocates for…

Machine Learning · Statistics 2025-05-19 Oskar Allerbo

Overparameterization in deep learning typically refers to settings where a trained neural network (NN) has representational capacity to fit the training data in many ways, some of which generalize well, while others do not. In the case of…

Machine Learning · Computer Science 2023-03-24 Edo Cohen-Karlik , Itamar Menuhin-Gruman , Raja Giryes , Nadav Cohen , Amir Globerson

The performance of the data-dependent neural tangent kernel (NTK; Jacot et al. (2018)) associated with a trained deep neural network (DNN) often matches or exceeds that of the full network. This implies that DNN training via gradient…

Machine Learning · Computer Science 2025-05-22 Johannes Schwab , Bryan Kelly , Semyon Malamud , Teng Andrea Xu

Despite their immense promise in performing a variety of learning tasks, a theoretical understanding of the limitations of Deep Neural Networks (DNNs) has so far eluded practitioners. This is partly due to the inability to determine the…

Machine Learning · Computer Science 2024-01-25 Saad Qadeer , Andrew Engel , Amanda Howard , Adam Tsou , Max Vargas , Panos Stinis , Tony Chiang

The early phase of training of deep neural networks is critical for their final performance. In this work, we study how the hyperparameters of stochastic gradient descent (SGD) used in the early phase of training affect the rest of the…

Machine Learning · Computer Science 2020-02-25 Stanislaw Jastrzebski , Maciej Szymczak , Stanislav Fort , Devansh Arpit , Jacek Tabor , Kyunghyun Cho , Krzysztof Geras

Modern machine learning models are often trained in a setting where the number of parameters exceeds the number of training samples. To understand the implicit bias of gradient descent in such overparameterized models, prior work has…

Machine Learning · Statistics 2025-10-29 Hannes Matt , Dominik Stöger

Traditional algorithms to optimize artificial neural networks when confronted with a supervised learning task are usually exploitation-type relaxational dynamics such as gradient descent (GD). Here, we explore the dynamics of the neural…

Machine Learning · Computer Science 2026-03-10 Pedro Jiménez-González , Miguel C. Soriano , Lucas Lacasa

Natural gradient descent has proven effective at mitigating the effects of pathological curvature in neural network optimization, but little is known theoretically about its convergence properties, especially for \emph{nonlinear} networks.…

Machine Learning · Statistics 2019-10-29 Guodong Zhang , James Martens , Roger Grosse
‹ Prev 1 4 5 6 7 8 10 Next ›