English
Related papers

Related papers: Kantorovich--Kernel Neural Operators: Approximatio…

200 papers

This article presents the inverse of the kernel operator associated with the complete quadratic Lyapunov-Krasovskii functional for coupled differential-functional equations when the kernel operator is separable. Similar to the case of…

Systems and Control · Computer Science 2017-03-31 Guoying Miao , Matthew M. Peet , Keqin Gu

The concept of mixed norm spaces has emerged as a significant interest in fields such as harmonic analysis. In addition, the problem of function approximation through sampling series has been particularly noteworthy in the realm of…

Functional Analysis · Mathematics 2025-07-24 Priyanka Majethiya , Shivam Bajpeyi , Dhiraj Patel

In the present article, we propose the new class positive linear operators, which discrete type depending on a real parameters. These operators are similar to Jain operators but its approximation properties are different then Jain…

Classical Analysis and ODEs · Mathematics 2019-04-19 Prashantkumar Patel

With the impressive capability to capture visual content, deep convolutional neural networks (CNN) have demon- strated promising performance in various vision-based ap- plications, such as classification, recognition, and objec- t…

Computer Vision and Pattern Recognition · Computer Science 2015-09-16 Zhen Liu

While deep learning has achieved remarkable success across a wide range of applications, its theoretical understanding of representation learning remains limited. Deep neural kernels provide a principled framework to interpret…

Machine Learning · Computer Science 2025-11-11 Yong-Ming Tian , Shuang Liang , Shao-Qun Zhang , Feng-Lei Fan

We consider solving a probably infinite dimensional operator equation, where the operator is not modeled by physical laws but is specified indirectly via training pairs of the input-output relation of the operator. Neural operators have…

Numerical Analysis · Mathematics 2026-05-06 Otmar Scherzer , Thi Lan Nhi Vu , Jikai Yan

Inspired by the close relationship between Kolmogorov complexity and unsupervised machine learning, we explore quantum circuit complexity, an important concept in quantum computation and quantum information science, as a pivot to understand…

Quantum Physics · Physics 2026-04-29 Yanming Che , Clemens Gneiting , Xiaoguang Wang , Franco Nori

This article provides a power series summability based Korovkin type approximation theorem for any fuzzy sequence of positive linear operators. Using the notion of fuzzy modulus of smoothness, we also derive an associated approximation…

General Mathematics · Mathematics 2022-02-07 Behar Baxhaku , Purshottam Narain Agrawal , Rahul Shukla

Neural operators have achieved significant success in modern scientific computing due to their flexibility and strong generalization capabilities. Existing models, however, primarily rely on first-order kernel integral approximations, which…

Machine Learning · Computer Science 2026-05-22 Pengyuan Zhu , Ivor W. Tsang , Yueming Lyu

Deep neural networks are an attractive alternative for simulating complex dynamical systems, as in comparison to traditional scientific computing methods, they offer reduced computational costs during inference and can be trained directly…

Machine Learning · Computer Science 2024-05-01 Katarzyna Michałowska , Somdatta Goswami , George Em Karniadakis , Signe Riemer-Sørensen

In this paper we show how specific families of positive definite kernels serve as powerful tools in analyses of iteration algorithms for multiple layer feedforward Neural Network models. Our focus is on particular kernels that adapt well to…

Machine Learning · Computer Science 2023-01-09 Palle E. T. Jorgensen , Myung-Sin Song , James Tian

We review the basic properties of paired operators and their adjoints, the transposed paired operators, with particular reference to commutation relations, and we study the properties of their kernels, bringing out their similarities and…

Functional Analysis · Mathematics 2024-12-23 M. Cristina Câmara , Jonathan R. Partington

Current Deep Learning approaches have been very successful using convolutional neural networks (CNN) trained on large graphical processing units (GPU)-based computers. Three limitations of this approach are: 1) they are based on a simple…

Neural and Evolutionary Computing · Computer Science 2017-07-17 Thomas E. Potok , Catherine Schuman , Steven R. Young , Robert M. Patton , Federico Spedalieri , Jeremy Liu , Ke-Thia Yao , Garrett Rose , Gangotree Chakma

The Convolutional Neural Networks (CNNs) have been the dominant and effective approach for general computer vision tasks. Recently, Kolmogorov-Arnold neural networks (KANs), based on the Kolmogorov-Arnold representation theorem, have shown…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Zhaoxiang Liu , Zhicheng Ma , Kaikai Zhao , Kai Wang , Shiguo Lian

Classical integral representation of the Mellin type kernel in terms of the Laplace integral gives an idea to construct a new class of non-convolution (index) transforms. Particular examples give the Kontorovich-Lebedev-like transformation…

Classical Analysis and ODEs · Mathematics 2012-09-11 Semyon Yakubovich

In this study, we examine the convergence characteristics of the Max-Product Kantrovich type exponential sampling series within the weighted space of log-uniformly continuous and bounded functions. The research focuses on deriving…

Functional Analysis · Mathematics 2025-04-29 Satyaranjan Pradhan , Madan Mohan Soren

This paper deals with the approximations of Durrmeyer type generalization of Szasz-Mirakjan operators. We establish the direct results, quantitative Voronovskaya type theorem, Gruss type theorem, A-statistical convergence, rate of…

Functional Analysis · Mathematics 2019-12-02 Rishikesh Yadav , Ramakanta Meher , Vishnu Narayan Mishra

In this paper, we study the convergence in variation for the generalized sampling operators based upon averaged-type kernels and we obtain a characterization of absolutely continuous functions. This result is proved exploiting a relation…

Functional Analysis · Mathematics 2017-10-13 Laura Angeloni , Danilo Costarelli , Gianluca Vinti

Neural operator learning methods have garnered significant attention in scientific computing for their ability to approximate infinite-dimensional operators. However, increasing their complexity often fails to substantially improve their…

The aim of this research is to examine various statistical approximation properties with respect to Kantorovich \textit{\text{\texthtq}}-Baskakov operators using wavelets. We discuss and investigate a weighted statistical approximation…

General Mathematics · Mathematics 2023-05-18 Mohammad Ayman-Mursaleen , Bishnu P. Lamichhane , Adem Kiliçman , Norazak Senu