English
Related papers

Related papers: Gradient Descent can Learn Less Over-parameterized…

200 papers

Neural networks with REctified Linear Unit (ReLU) activation functions (a.k.a. ReLU networks) have achieved great empirical success in various domains. Nonetheless, existing results for learning ReLU networks either pose assumptions on the…

Machine Learning · Statistics 2019-05-01 Gang Wang , Georgios B. Giannakis , Jie Chen

In this paper, we study the generalization performance of min $\ell_2$-norm overfitting solutions for the neural tangent kernel (NTK) model of a two-layer neural network with ReLU activation that has no bias term. We show that, depending on…

Machine Learning · Computer Science 2023-03-09 Peizhong Ju , Xiaojun Lin , Ness B. Shroff

We give a simple proof for the global convergence of gradient descent in training deep ReLU networks with the standard square loss, and show some of its improvements over the state-of-the-art. In particular, while prior works require all…

Machine Learning · Computer Science 2021-06-14 Quynh Nguyen

A recent breakthrough in deep learning theory shows that the training of over-parameterized deep neural networks can be characterized by a kernel function called \textit{neural tangent kernel} (NTK). However, it is known that this type of…

Machine Learning · Computer Science 2020-10-07 Zixiang Chen , Yuan Cao , Quanquan Gu , Tong Zhang

While deep learning is successful in a number of applications, it is not yet well understood theoretically. A satisfactory theoretical characterization of deep learning however, is beginning to emerge. It covers the following questions: 1)…

Machine Learning · Computer Science 2019-08-27 Tomaso Poggio , Andrzej Banburski , Qianli Liao

Neural networks can be trained to solve regression problems by using gradient-based methods to minimize the square loss. However, practitioners often prefer to reformulate regression as a classification problem, observing that training on…

Machine Learning · Computer Science 2023-03-02 Lawrence Stewart , Francis Bach , Quentin Berthet , Jean-Philippe Vert

We study the relative power of learning with gradient descent on differentiable models, such as neural networks, versus using the corresponding tangent kernels. We show that under certain conditions, gradient descent achieves small error…

Machine Learning · Computer Science 2021-03-02 Eran Malach , Pritish Kamath , Emmanuel Abbe , Nathan Srebro

Machine Unlearning aims to remove specific data from trained models, addressing growing privacy and ethical concerns. We provide a theoretical analysis of a simple and widely used method - gradient ascent - used to reverse the influence of…

Machine Learning · Computer Science 2025-10-17 Odelia Melamed , Gilad Yehudai , Gal Vardi

The implicit bias towards solutions with favorable properties is believed to be a key reason why neural networks trained by gradient-based optimization can generalize well. While the implicit bias of gradient flow has been widely studied…

Machine Learning · Computer Science 2023-10-31 Yiwen Kou , Zixiang Chen , Quanquan Gu

Significant theoretical work has established that in specific regimes, neural networks trained by gradient descent behave like kernel methods. However, in practice, it is known that neural networks strongly outperform their associated…

Machine Learning · Computer Science 2022-07-01 Alex Damian , Jason D. Lee , Mahdi Soltanolkotabi

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…

Machine Learning · Computer Science 2022-01-03 Zixiang Chen , Yuan Cao , Difan Zou , Quanquan Gu

In this work, we provide a characterization of the feature-learning process in two-layer ReLU networks trained by gradient descent on the logistic loss following random initialization. We consider data with binary labels that are generated…

Machine Learning · Computer Science 2023-09-15 Spencer Frei , Niladri S. Chatterji , Peter L. Bartlett

Deep neural networks (DNNs) have demonstrated dominating performance in many fields; since AlexNet, networks used in practice are going wider and deeper. On the theoretical side, a long line of works has been focusing on training neural…

Machine Learning · Computer Science 2019-06-18 Zeyuan Allen-Zhu , Yuanzhi Li , Zhao Song

We revisit the problem of learning a single neuron with ReLU activation under Gaussian input with square loss. We particularly focus on the over-parameterization setting where the student network has $n\ge 2$ neurons. We prove the global…

Machine Learning · Computer Science 2023-10-11 Weihang Xu , Simon S. Du

We study the overparametrization bounds required for the global convergence of stochastic gradient descent algorithm for a class of one hidden layer feed-forward neural networks, considering most of the activation functions used in…

Machine Learning · Computer Science 2022-11-17 Bartłomiej Polaczyk , Jacek Cyranka

We prove that two-layer (Leaky)ReLU networks initialized by e.g. the widely used method proposed by He et al. (2015) and trained using gradient descent on a least-squares loss are not universally consistent. Specifically, we describe a…

Machine Learning · Statistics 2022-06-10 David Holzmüller , Ingo Steinwart

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…

Machine Learning · Computer Science 2024-05-21 G. Welper

Deep learning models are often successfully trained using gradient descent, despite the worst case hardness of the underlying non-convex optimization problem. The key question is then under what conditions can one prove that optimization…

Machine Learning · Computer Science 2017-02-28 Alon Brutzkus , Amir Globerson

The ability of learning useful features is one of the major advantages of neural networks. Although recent works show that neural network can operate in a neural tangent kernel (NTK) regime that does not allow feature learning, many works…

Machine Learning · Computer Science 2024-11-06 Mo Zhou , Rong Ge

Normalized gradient descent has shown substantial success in speeding up the convergence of exponentially-tailed loss functions (which includes exponential and logistic losses) on linear classifiers with separable data. In this paper, we go…

Machine Learning · Computer Science 2023-06-28 Hossein Taheri , Christos Thrampoulidis