English
Related papers

Related papers: Convergence beyond the over-parameterized regime u…

200 papers

We propose a novel Rayleigh quotient based sparse quadratic dimension reduction method - named QUADRO (Quadratic Dimension Reduction via Rayleigh Optimization) - for analyzing high- dimensional data. Unlike in the linear setting where…

Methodology · Statistics 2015-07-30 Jianqing Fan , Zheng Tracy Ke , Han Liu , Lucy Xia

In this paper we study the convergence of online gradient descent algorithms in reproducing kernel Hilbert spaces (RKHSs) without regularization. We establish a sufficient condition and a necessary condition for the convergence of excess…

Machine Learning · Computer Science 2017-08-11 Yunwen Lei , Lei Shi , Zheng-Chu Guo

In machine learning, overparameterization is associated with qualitative changes in the empirical risk landscape, which can lead to more efficient training dynamics. For many parameterized models used in statistical learning, there exists a…

Quantum Physics · Physics 2023-07-11 Andrea Delgado , Francisco Rios , Kathleen E. Hamilton

The use of transfer learning with deep neural networks has increasingly become widespread for deploying well-tested computer vision systems to newer domains, especially those with limited datasets. We describe a transfer learning use case…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Rashik Shadman , M. G. Sarwar Murshed , Edward Verenich , Alvaro Velasquez , Faraz Hussain

The study of Neural Tangent Kernels (NTKs) has provided much needed insight into convergence and generalization properties of neural networks in the over-parametrized (wide) limit by approximating the network using a first-order Taylor…

Machine Learning · Statistics 2023-02-02 Alistair Shilton , Sunil Gupta , Santu Rana , Svetha Venkatesh

Neural networks trained to minimize the logistic (a.k.a. cross-entropy) loss with gradient-based methods are observed to perform well in many supervised classification tasks. Towards understanding this phenomenon, we analyze the training…

Optimization and Control · Mathematics 2020-06-23 Lenaic Chizat , Francis Bach

Deep learning has aroused extensive attention due to its great empirical success. The efficiency of the block coordinate descent (BCD) methods has been recently demonstrated in deep neural network (DNN) training. However, theoretical…

Optimization and Control · Mathematics 2019-05-14 Jinshan Zeng , Tim Tsz-Kit Lau , Shaobo Lin , Yuan Yao

We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent. We show that these learned optimizers exhibit a remarkable degree of transfer in that they can be used to efficiently optimize a broad…

The aim of this article is to provide a firm mathematical foundation for the application of deep gradient flow methods (DGFMs) for the solution of (high-dimensional) partial differential equations (PDEs). We decompose the generalization…

Numerical Analysis · Mathematics 2026-02-26 Chenguang Liu , Antonis Papapantoleon , Jasper Rou

Machine learning methods are commonly used to solve inverse problems, wherein an unknown signal must be estimated from few indirect measurements generated via a known acquisition procedure. In particular, neural networks perform well…

Machine Learning · Computer Science 2025-12-05 Hannah Laus , Suzanna Parkinson , Vasileios Charisopoulos , Felix Krahmer , Rebecca Willett

Aimed at explaining the surprisingly good generalization behavior of overparameterized deep networks, recent works have developed a variety of generalization bounds for deep learning, all based on the fundamental learning-theoretic…

Machine Learning · Computer Science 2021-10-19 Vaishnavh Nagarajan , J. Zico Kolter

We study geometric properties of the gradient flow for learning deep linear convolutional networks. For linear fully connected networks, it has been shown recently that the corresponding gradient flow on parameter space can be written as a…

Machine Learning · Computer Science 2026-04-07 El Mehdi Achour , Kathlén Kohn , Holger Rauhut

A longstanding goal in deep learning research has been to precisely characterize training and generalization. However, the often complex loss landscapes of neural networks have made a theory of learning dynamics elusive. In this work, we…

We continue a long line of research aimed at proving convergence of depth 2 neural networks, trained via gradient descent, to a global minimum. Like in many previous works, our model has the following features: regression with quadratic…

Machine Learning · Computer Science 2022-12-06 Alexander Razborov

Deep neural networks are widely used prediction algorithms whose performance often improves as the number of weights increases, leading to over-parametrization. We consider a two-layered neural network whose first layer is frozen while the…

Machine Learning · Computer Science 2023-04-10 Roman Worschech , Bernd Rosenow

We develop a method for training neural networks on Boolean data in which the values at all nodes are strictly $\pm 1$, and the resulting models are typically equivalent to networks whose nonzero weights are also $\pm 1$. The method…

Machine Learning · Computer Science 2026-02-20 Veit Elser , Manish Krishan Lal

Deep learning is computationally intensive, with significant efforts focused on reducing arithmetic complexity, particularly regarding energy consumption dominated by data movement. While existing literature emphasizes inference, training…

Machine Learning · Statistics 2025-06-09 Van Minh Nguyen , Cristian Ocampo , Aymen Askri , Louis Leconte , Ba-Hien Tran

We consider machine learning applications that train a model by leveraging data distributed over a trusted network, where communication constraints can create a performance bottleneck. A number of recent approaches propose to overcome this…

Machine Learning · Computer Science 2021-09-10 Osama A. Hanna , Yahya H. Ezzeldin , Christina Fragouli , Suhas Diggavi

We study gradient flows for loss landscapes of fully connected feedforward neural networks with commonly used continuously differentiable activation functions such as the logistic, hyperbolic tangent, softplus or GELU function. We prove…

Machine Learning · Computer Science 2026-01-13 Julian Kranz , Davide Gallon , Steffen Dereich , Arnulf Jentzen

Stochastic differentiable approximation schemes are widely used for solving high dimensional problems. Most of existing methods satisfy some desirable properties, including conditional descent inequalities, and almost sure (a.s.)…

Optimization and Control · Mathematics 2024-11-08 Jean-Baptiste Fest , Audrey Repetti , Emilie Chouzenoux
‹ Prev 1 4 5 6 7 8 10 Next ›