Representation Equivalent Neural Operators: a Framework for Alias-free Operator Learning

Abstract

Recently, operator learning, or learning mappings between infinite-dimensional function spaces, has garnered significant attention, notably in relation to learning partial differential equations from data. Conceptually clear when outlined on paper, neural operators necessitate discretization in the transition to computer implementations. This step can compromise their integrity, often causing them to deviate from the underlying operators. This research offers a fresh take on neural operators with a framework Representation equivalent Neural Operators (ReNO) designed to address these issues. At its core is the concept of operator aliasing, which measures inconsistency between neural operators and their discrete representations. We explore this for widely-used operator learning techniques. Our findings detail how aliasing introduces errors when handling different discretizations and grids and loss of crucial continuous structures. More generally, this framework not only sheds light on existing challenges but, given its constructive and broad nature, also potentially offers tools for developing new neural operators.

arXiv comment28 pages

Cited by in corpus (5)

• Kolmogorov Arnold Informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov Arnold Networks
• Plasma Surrogate Modelling using Fourier Neural Operators
• Neural Integral Equations
• On the Effectiveness of Neural Operators at Zero-Shot Weather Downscaling
• Continuous Generative Neural Networks: A Wavelet-Based Architecture in Function Spaces