English
Related papers

Related papers: Neural reproducing kernel Banach spaces and repres…

200 papers

Substring kernels are classical tools for representing biological sequences or text. However, when large amounts of annotated data are available, models that allow end-to-end training such as neural networks are often preferred. Links…

Machine Learning · Statistics 2019-10-18 Dexiong Chen , Laurent Jacob , Julien Mairal

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 article delves into the study of the theory of regularized learning in Banach spaces for linear-functional data. It encompasses discussions on representer theorems, pseudo-approximation theorems, and convergence theorems. Regularized…

Machine Learning · Computer Science 2025-03-05 Qi Ye

In this paper, we introduce a generalization of Reproducing Kernel Banach Spaces (RKBS), which we term \emph{Generalized Reproducing Kernel Banach Spaces} (GRKBS). The motivation stems from recent results showing that classical fully…

Functional Analysis · Mathematics 2026-01-21 Raul Felipe-Sosa

We define a neural network in infinite dimensional spaces for which we can show the universal approximation property. Indeed, we derive approximation results for continuous functions from a Fr\'echet space $\X$ into a Banach space $\Y$. The…

Functional Analysis · Mathematics 2022-05-18 Fred Espen Benth , Nils Detering , Luca Galimberti

In this paper, we establish a novel connection between the metric entropy growth and the embeddability of function spaces into reproducing kernel Hilbert/Banach spaces. Metric entropy characterizes the information complexity of function…

Numerical Analysis · Mathematics 2025-08-28 Yiping Lu , Daozhe Lin , Qiang Du

Deep neural networks can empirically perform efficient hierarchical learning, in which the layers learn useful representations of the data. However, how they make use of the intermediate representations are not explained by recent theories…

Machine Learning · Computer Science 2021-03-08 Minshuo Chen , Yu Bai , Jason D. Lee , Tuo Zhao , Huan Wang , Caiming Xiong , Richard Socher

In this work, we consider the problem of learning nonlinear operators that correspond to discrete-time nonlinear dynamical systems with inputs. Given an initial state and a finite input trajectory, such operators yield a finite output…

Optimization and Control · Mathematics 2024-12-25 Mircea Lazar

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…

Machine Learning · Computer Science 2022-01-11 Calvin Murdock , George Cazenavette , Simon Lucey

The representer theorem is one of the most important mathematical foundations for regularised learning and kernel methods. Classical formulations of the theorem state sufficient conditions under which a regularisation problem on a Hilbert…

Functional Analysis · Mathematics 2019-11-04 Kevin Schlegel

There is some theoretical evidence that deep neural networks with multiple hidden layers have a potential for more efficient representation of multidimensional mappings than shallow networks with a single hidden layer. The question is…

Machine Learning · Computer Science 2019-10-08 Bernhard Bermeitinger , Tomas Hrycej , Siegfried Handschuh

Deep networks are often considered to be more expressive than shallow ones in terms of approximation. Indeed, certain functions can be approximated by deep networks provably more efficiently than by shallow ones, however, no tractable…

Machine Learning · Statistics 2021-08-27 Alberto Bietti , Francis Bach

It has long been conjectured that hypotheses spaces suitable for data that is compositional in nature, such as text or images, may be more efficiently represented with deep hierarchical networks than with shallow ones. Despite the vast…

Neural and Evolutionary Computing · Computer Science 2016-10-18 Nadav Cohen , Or Sharir , Amnon Shashua

We consider a general regularised interpolation problem for learning a parameter vector from data. The well known representer theorem says that under certain conditions on the regulariser there exists a solution in the linear span of the…

Functional Analysis · Mathematics 2019-05-14 Kevin Schlegel

Despite their ubiquity in core AI fields like natural language processing, the mechanics of deep attention-based neural networks like the Transformer model are not fully understood. In this article, we present a new perspective towards…

Machine Learning · Computer Science 2021-06-04 Matthew A. Wright , Joseph E. Gonzalez

Sparsity of a learning solution is a desirable feature in machine learning. Certain reproducing kernel Banach spaces (RKBSs) are appropriate hypothesis spaces for sparse learning methods. The goal of this paper is to understand what kind of…

Functional Analysis · Mathematics 2024-03-08 Rui Wang , Yuesheng Xu , Mingsong Yan

In this paper we provide a finite-sample and an infinite-sample representer theorem for the concatenation of (linear combinations of) kernel functions of reproducing kernel Hilbert spaces. These results serve as mathematical foundation for…

Machine Learning · Computer Science 2018-06-08 Bastian Bohn , Michael Griebel , Christian Rieger

We develop Banach spaces for ReLU neural networks of finite depth $L$ and infinite width. The spaces contain all finite fully connected $L$-layer networks and their $L^2$-limiting objects under bounds on the natural path-norm. Under this…

Machine Learning · Statistics 2020-07-31 Weinan E , Stephan Wojtowytsch

We present necessary and sufficient conditions to hold true a Kramer type sampling theorem over semi-inner product reproducing kernel Banach spaces. Under some sampling-type hypotheses over a sequence of functions on these Banach spaces it…

Functional Analysis · Mathematics 2018-07-09 Hernán D. Centeno , Juan M. Medina

Based on the tree architecture, the objective of this paper is to design deep neural networks with two or more hidden layers (called deep nets) for realization of radial functions so as to enable rotational invariance for near-optimal…

Machine Learning · Computer Science 2019-04-04 Charles K. Chui , Shao-Bo Lin , Ding-Xuan Zhou