English
Related papers

Related papers: Universal Approximation of Operators with Transfor…

200 papers

We introduce a positive linear operator acting on the Banach space of all continuous functions on the unit interval via the Moran model studied in population genetics. We show that this operator, named the Moran operator, uniformly…

Probability · Mathematics 2025-03-04 Takahiro Aoyama , Ryuya Namba

The Convolutional Neural Network (CNN) is one of the most prominent neural network architectures in deep learning. Despite its widespread adoption, our understanding of its universal approximation properties has been limited due to its…

Neural and Evolutionary Computing · Computer Science 2023-12-05 Geonho Hwang , Myungjoo Kang

For an operator ideal $\mathcal A$, we study the composition operator ideals ${\mathcal A}\circ{\mathcal K}$, ${\mathcal K}\circ{\mathcal A}$ and ${\mathcal K}\circ{\mathcal A}\circ{\mathcal K}$, where $\mathcal K$ is the ideal of compact…

Functional Analysis · Mathematics 2012-07-10 Anil Kumar Karn , Deba Prasad Sinha

The inception of spatial transcriptomics has allowed improved comprehension of tissue architectures and the disentanglement of complex underlying biological, physiological, and pathological processes through their positional contexts.…

Machine Learning · Computer Science 2023-02-02 Junaid Ahmed , Alhassan S. Yasin

In this dissertation I establish that a broad class of Banach *-algebras of infinite integral operators, defined by the property that the kernels of the elements of the algebras possess subexponential off-diagonal decay, is inverse closed…

Operator Algebras · Mathematics 2007-05-23 Scott Beaver

We study some basic properties of the class of universal operators on Hilbert space, and provide new examples of universal operators and universal pairs.

Functional Analysis · Mathematics 2017-02-20 Riikka Schroderus , Hans-Olav Tylli

We introduce a family of Banach spaces of measures, each containing the set of measures with density of bounded variation. These spaces are suitable for the study of weighted transfer operators of piecewise-smooth maps of the interval where…

Dynamical Systems · Mathematics 2014-03-21 Oliver Butterley

This paper offers a newly created integral approach for operators employing the orthogonal modified Laguerre polynomials and P\u{a}lt\u{a}nea basis. These operators approximate the functions over the interval $[0,\infty)$. Further, the…

Functional Analysis · Mathematics 2024-05-14 Kapil Kumar , Naokant Deo , Durvesh Kumar Verma

Universal approximation theorems are the foundations of classical neural networks, providing theoretical guarantees that the latter are able to approximate maps of interest. Recent results have shown that this can also be achieved in a…

Quantum Physics · Physics 2025-04-14 Lukas Gonon , Antoine Jacquier

A closed subspace of a Banach space $\cX$ is almost-invariant for a collection $\cS$ of bounded linear operators on $\cX$ if for each $T \in \cS$ there exists a finite-dimensional subspace $\cF_T$ of $\cX$ such that $T \cY \subseteq \cY +…

Functional Analysis · Mathematics 2012-04-23 Laurent W. Marcoux , Alexey I. Popov , Heydar Radjavi

The global homeomorphism theorem for quasiconformal maps describes the following specifically higher-dimensional phenomenon: {\em Locally invertible quasiconformal mapping $f: {\R}^{n} \to {\R}^{n}$ is globally invertible provided $n > 2$.}…

Complex Variables · Mathematics 2021-08-04 V. A. Zorich

Is there any theoretical guarantee for the approximation ability of neural networks? The answer to this question is the "Universal Approximation Theorem for Neural Networks". This theorem states that a neural network is dense in a certain…

Machine Learning · Computer Science 2021-02-23 Takato Nishijima

A bounded linear operator between Banach spaces is called {\it completely continuous} if it carries weakly convergent sequences into norm convergent sequences. Isolated is a universal operator for the class of non-completely-continuous…

Functional Analysis · Mathematics 2016-09-06 Maria Girardi , William B. Johnson

We introduce an abstract neural flow framework for neural networks and neural operators. The framework contains two continuous-depth models, namely neural flows with composition and separation structures, and covers both finite-dimensional…

Machine Learning · Computer Science 2026-05-27 Shuang Chen , Juncai He , Xue-Cheng Tai

Learning operators between infinitely dimensional spaces is an important learning task arising in wide applications in machine learning, imaging science, mathematical modeling and simulations, etc. This paper studies the nonparametric…

Machine Learning · Statistics 2022-01-04 Hao Liu , Haizhao Yang , Minshuo Chen , Tuo Zhao , Wenjing Liao

We describe generalizations of the universal approximation theorem for neural networks to maps invariant or equivariant with respect to linear representations of groups. Our goal is to establish network-like computational models that are…

Neural and Evolutionary Computing · Computer Science 2018-04-30 Dmitry Yarotsky

Motivated by the developing mathematics of deep learning, we build universal functions approximators of continuous maps between arbitrary Polish metric spaces $\mathcal{X}$ and $\mathcal{Y}$ using elementary functions between Euclidean…

Machine Learning · Computer Science 2023-07-25 Anastasis Kratsios , Chong Liu , Matti Lassas , Maarten V. de Hoop , Ivan Dokmanić

We use the injective envelope to study quasimultipliers of operator spaces. We prove that all representable operator algebra products that an operator space can be endowed with are induced by quasimultipliers. We obtain generalizations of…

Operator Algebras · Mathematics 2007-05-23 Masayoshi Kaneda , Vern I. Paulsen

Inversion of operators is a fundamental concept in data processing. Inversion of linear operators is well studied, supported by established theory. When an inverse either does not exist or is not unique, generalized inverses are used. Most…

Statistics Theory · Mathematics 2024-04-02 Eyal Gofer , Guy Gilboa

We study feedforward neural networks with inputs from a topological vector space (TVS-FNNs). Unlike traditional feedforward neural networks, TVS-FNNs can process a broader range of inputs, including sequences, matrices, functions and more.…

Machine Learning · Computer Science 2024-09-20 Vugar Ismailov