paper-with-me

Papers

Projection Methods for Operator Learning and Universal Approximation

2024-06-18 · Emanuele Zappala

We obtain a new universal approximation theorem for continuous (possibly nonlinear) operators on arbitrary Banach spaces using the Leray-Schauder mapping. Moreover, we introduce and study a method for operator learning in Banach spaces $L^p$ of functions with multiple variables, based on orthogonal projections on polynomial bases. We derive a universal approximation result for operators where we learn a linear projection and a finite dimensional mapping under some additional assumptions. For the case of $p=2$, we give some sufficient conditions for the approximation results to hold. This article serves as the theoretical framework for a deep learning methodology in operator learning.

📄 PDF Abstract BibTeX arXiv:2406.12264

Code (0)

등록된 구현이 없습니다.

Tasks

Operator learning

Similar Papers 제목 키워드 기반

RandONet: Shallow-Networks with Random Projections for learning linear and nonlinear operators

2024-06-08 · Gianluca Fabiani, Ioannis G. Kevrekidis, Constantinos Siettos, Athanasios N. Yannacopoulos

Deep Operator Networks (DeepOnets) have revolutionized the domain of scientific machine learning for the solution of the inverse problem for dynamical systems. However, their implementation necessitates optimizing a high…

Universal Approximation of Operators with Transformers and Neural Integral Operators

2024-09-01 · Emanuele Zappala, Maryam Bagherian

We study the universal approximation properties of transformers and neural integral operators for operators in Banach spaces. In particular, we show that the transformer architecture is a universal approximator of integr…

New universal operator approximation theorem for encoder-decoder architectures (Preprint)

2025-03-31 · Janek Gödeke, Pascal Fernsel

Motivated by the rapidly growing field of mathematics for operator approximation with neural networks, we present a novel universal operator approximation theorem for a broad class of encoder-decoder architectures. In th…

DecoderOperator learning

Nonlocality and Nonlinearity Implies Universality in Operator Learning

2023-04-26 · Samuel Lanthaler, Zongyi Li, Andrew M. Stuart

Neural operator architectures approximate operators between infinite-dimensional Banach spaces of functions. They are gaining increased attention in computational science and engineering, due to their potential both to a…

Operator learning

Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations

2026-05-21 · Shuang Chen, Juncai He, Xue-Cheng Tai arxiv

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…