English
Related papers

Related papers: Why High-rank Neural Networks Generalize?: An Alge…

200 papers

We consider neural networks with a single hidden layer and non-decreasing homogeneous activa-tion functions like the rectified linear units. By letting the number of hidden units grow unbounded and using classical non-Euclidean…

Machine Learning · Computer Science 2016-11-01 Francis Bach

Usually, complex-valued RKHS are presented as an straightforward application of the real-valued case. In this paper we prove that this procedure yields a limited solution for regression. We show that another kernel, here denoted as pseudo…

Most complex machine learning and modelling techniques are prone to over-fitting and may subsequently generalise poorly to future data. Artificial neural networks are no different in this regard and, despite having a level of implicit…

Machine Learning · Statistics 2022-05-26 Vincent Szolnoky , Viktor Andersson , Balazs Kulcsar , Rebecka Jörnsten

This paper studies the problem of learning weighted automata from a finite labeled training sample. We consider several general families of weighted automata defined in terms of three different measures: the norm of an automaton's weights,…

Machine Learning · Computer Science 2016-10-26 Borja Balle , Mehryar Mohri

In this paper, the robustness and accuracy of the deep neural network (DNN) was enhanced by introducing the $L_{2,\infty}$ normalization of the weight matrices of the DNN with Relu as the activation function. It is proved that the…

Machine Learning · Statistics 2020-10-13 Lijia Yu , Xiao-Shan Gao

One of the fundamental challenges in the deep learning community is to theoretically understand how well a deep neural network generalizes to unseen data. However, current approaches often yield generalization bounds that are either too…

Machine Learning · Computer Science 2024-07-23 Chengli Tan , Jiangshe Zhang , Junmin Liu

A complete understanding of the widely used over-parameterized deep networks is a key step for AI. In this work we try to give a geometric picture of over-parameterized deep networks using our geometrization scheme. We show that the…

Machine Learning · Computer Science 2019-02-12 Xiao Dong , Ling Zhou

The computational complexity of kernel methods has often been a major barrier for applying them to large-scale learning problems. We argue that this barrier can be effectively overcome. In particular, we develop methods to scale up kernel…

Reproducing kernel Hilbert spaces (RKHSs) are key elements of many non-parametric tools successfully used in signal processing, statistics, and machine learning. In this work, we aim to address three issues of the classical RKHS based…

Signal Processing · Electrical Eng. & Systems 2019-05-09 Maria Peifer , Luiz. F. O. Chamon , Santiago Paternain , Alejandro Ribeiro

We investigate the approximation capabilities of dense neural networks. While universal approximation theorems establish that sufficiently large architectures can approximate arbitrary continuous functions if there are no restrictions on…

Machine Learning · Computer Science 2026-05-19 Levi Rauchwerger , Stefanie Jegelka , Ron Levie

By universal formulas we understand parameterized analytic expressions that have a fixed complexity, but nevertheless can approximate any continuous function on a compact set. There exist various examples of such formulas, including some in…

Machine Learning · Computer Science 2023-11-08 Dmitry Yarotsky

Deep Neural Networks reached state-of-the-art performance across numerous domains, but this progress has come at the cost of increasingly large and over-parameterized models, posing serious challenges for deployment on resource-constrained…

Machine Learning · Computer Science 2026-02-04 Dario Malchiodi , Mattia Ferraretto , Marco Frasca

We propose a new decentralized robust kernel-based learning algorithm within the framework of reproducing kernel Hilbert spaces (RKHSs) by utilizing a networked system that can be represented as a connected graph. The robust loss function…

Machine Learning · Computer Science 2025-08-18 Zhan Yu , Zhongjie Shi , Ding-Xuan Zhou

We investigate a recently proposed family of positive-definite kernels that mimic the computation in large neural networks. We examine the properties of these kernels using tools from differential geometry; specifically, we analyze the…

Machine Learning · Computer Science 2011-12-19 Youngmin Cho , Lawrence K. Saul

Sample reweighting is one of the most widely used methods for correcting the error of least squares learning algorithms in reproducing kernel Hilbert spaces (RKHS), that is caused by future data distributions that are different from the…

Machine Learning · Computer Science 2023-07-24 Duc Hoan Nguyen , Sergei V. Pereverzyev , Werner Zellinger

A central question in deep learning is to understand the functions learned by deep networks. What is their approximation class? Do the learned weights and representations depend on initialization? Previous empirical work has evidenced that…

Machine Learning · Computer Science 2024-10-28 Florentin Guth , Brice Ménard , Gaspar Rochette , Stéphane Mallat

This paper presents several novel generalization bounds for the problem of learning kernels based on the analysis of the Rademacher complexity of the corresponding hypothesis sets. Our bound for learning kernels with a convex combination of…

Artificial Intelligence · Computer Science 2009-12-18 Corinna Cortes , Mehryar Mohri , Afshin Rostamizadeh

Modern Machine Learning (ML) and Deep Neural Networks (DNNs) often operate on high-dimensional data and rely on overparameterized models, where classical low-dimensional intuitions break down. In particular, the proportional regime where…

Machine Learning · Statistics 2026-04-17 Zhenyu Liao , Michael W. Mahoney

Kernel methods are successful approaches for different machine learning problems. This success is mainly rooted in using feature maps and kernel matrices. Some methods rely on the eigenvalues/eigenvectors of the kernel matrix, while for…

Machine Learning · Computer Science 2012-02-20 Nima Reyhani , Hideitsu Hino , Ricardo Vigario

We study generalization properties of distributed algorithms in the setting of nonparametric regression over a reproducing kernel Hilbert space (RKHS). We first investigate distributed stochastic gradient methods (SGM), with mini-batches…

Machine Learning · Statistics 2018-11-06 Junhong Lin , Volkan Cevher