Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yadav, Abhishek, Singh, Uaday, Dai, Feng
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.07886
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912819585220608
author Yadav, Abhishek
Singh, Uaday
Dai, Feng
author_facet Yadav, Abhishek
Singh, Uaday
Dai, Feng
contents In this paper, we develop a multivariate framework for approximation by max-min neural network operators. Building on the recent advances in approximation theory by neural network operators, particularly, the univariate max-min operators, we propose and analyze new multivariate operators activated by sigmoidal functions. We establish pointwise and uniform convergence theorems and derive quantitative estimates for the order of approximation via modulus of continuity and multivariate generalized absolute moment. Our results demonstrate that multivariate max-min structure of operators, besides their algebraic elegance, provide efficient and stable approximation tools in both theoretical and applied settings.
format Preprint
id arxiv_https___arxiv_org_abs_2601_07886
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Max-Min Neural Network Operators For Approximation of Multivariate Functions
Yadav, Abhishek
Singh, Uaday
Dai, Feng
Machine Learning
00A05(Primary), 41A25(Secondary), 41A35 (Secondary), 41A36 (Secondary)
In this paper, we develop a multivariate framework for approximation by max-min neural network operators. Building on the recent advances in approximation theory by neural network operators, particularly, the univariate max-min operators, we propose and analyze new multivariate operators activated by sigmoidal functions. We establish pointwise and uniform convergence theorems and derive quantitative estimates for the order of approximation via modulus of continuity and multivariate generalized absolute moment. Our results demonstrate that multivariate max-min structure of operators, besides their algebraic elegance, provide efficient and stable approximation tools in both theoretical and applied settings.
title Max-Min Neural Network Operators For Approximation of Multivariate Functions
topic Machine Learning
00A05(Primary), 41A25(Secondary), 41A35 (Secondary), 41A36 (Secondary)
url https://arxiv.org/abs/2601.07886