paper-with-me

홈 › Papers

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

2023-05-31 · NeurIPS 2023 11

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.

📄 PDF Abstract BibTeX arXiv:2305.19913

Code (0)

등록된 구현이 없습니다.

Tasks

Operator learning

Similar Papers 제목 키워드 기반

Frequency Pooling: Shift-Equivalent and Anti-Aliasing Downsampling

2021-09-24 · Zhendong Zhang

Convolution utilizes a shift-equivalent prior of images, thus leading to great success in image processing tasks. However, commonly used poolings in convolutional neural networks (CNNs), such as max-pooling, average-pool…

image-classificationImage Classification

Non-uniform Array and Frequency Spacing for Regularization-free Gridless DOA

2024-01-12 · Yifan Wu, Michael B. Wakin, Peter Gerstoft

Gridless direction-of-arrival (DOA) estimation with multiple frequencies can be applied in acoustics source localization problems. We formulate this as an atomic norm minimization (ANM) problem and derive an equivalent r…

Frequency Pooling: Shift-Equivalent and Anti-Aliasing Down Sampling

2019-09-25 · Zhendong Zhang, Cheolkon Jung

Convolutional layer utilizes the shift-equivalent prior of images which makes it a great success for image processing. However, commonly used down sampling methods in convolutional neural networks (CNNs), such as max-poo…

Alias-Free ViT: Fractional Shift Invariance via Linear Attention

2025-10-26 · Hagay Michaeli, Daniel Soudry arxiv

Transformers have emerged as a competitive alternative to convnets in vision tasks, yet they lack the architectural inductive bias of convnets, which may hinder their potential performance. Specifically, Vision Transform…

Image Classification

Convex Optimization With Abstract Linear Operators

2015-12-01 · ICCV 2015 12 · Steven Diamond, Stephen Boyd

We introduce a convex optimization modeling framework that transforms a convex optimization problem expressed in a form natural and convenient for the user into an equivalent cone program in a way that preserves fast lin…