paper-with-me

Papers

Rotation Equivariant Operators for Machine Learning on Scalar and Vector Fields

2021-08-21 · Paul Shen, Michael Herbst, Venkat Viswanathan

We develop theory and software for rotation equivariant operators on scalar and vector fields, with diverse applications in simulation, optimization and machine learning. Rotation equivariance (covariance) means all fields in the system rotate together, implying spatially invariant dynamics that preserve symmetry. Extending the convolution theorems of linear time invariant systems, we theorize that linear equivariant operators are characterized by tensor field convolutions using an appropriate product between the input field and a radially symmetric kernel field. Most Green's functions and differential operators are in fact equivariant operators, which can also fit unknown symmetry preserving dynamics by parameterizing the radial function. We implement the Julia package EquivariantOperators.jl for fully differentiable finite difference equivariant operators on scalar, vector and higher order tensor fields in 2d/3d. It can run forwards for simulation or image processing, or be back propagated for computer vision, inverse problems and optimal control. Code at https://aced-differentiate.github.io/EquivariantOperators.jl/

📄 PDF Abstract BibTeX arXiv:2108.09541

Code (1)

aced-differentiate/EquivariantOperators.jl 공식 구현

Tasks

BIG-bench Machine LearningTranslation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

When Do Geometric Algebra Layers Beat Scalarization? A Controlled Study on SO(3)-Equivariant Vector Laws

2026-07-07 · Fabien Polly arxiv

Compact networks built from Clifford algebra Cl(3,0) primitives are exactly SO(3)-equivariant and learn synthetic 3D vector laws from few samples. We ask whether the geometric algebra structure itself contributes anythin…

Scalars are universal: Equivariant machine learning, structured like classical physics

2021-06-11 · NeurIPS 2021 12 · Soledad Villar, David W. Hogg, Kate Storey-Fisher, Weichi Yao 외

There has been enormous progress in the last few years in designing neural networks that respect the fundamental symmetries and coordinate freedoms of physical law. Some of these frameworks make use of irreducible repres…

BIG-bench Machine LearningTranslation

VN-Transformer: Rotation-Equivariant Attention for Vector Neurons

2022-06-08 · Serge Assaad, Carlton Downey, Rami Al-Rfou, Nigamaa Nayakanti 외

Rotation equivariance is a desirable property in many practical applications such as motion forecasting and 3D perception, where it can offer benefits like sample efficiency, better generalization, and robustness to inpu…

3D Shape ClassificationMotion Forecasting

SO(3)-Equivariant Neural Networks for Learning Vector Fields on Spheres

2025-03-12 · Francesco Ballerin, Nello Blaser, Erlend Grong

Analyzing vector fields on the sphere, such as wind speed and direction on Earth, is a difficult task. Models should respect both the rotational symmetries of the sphere and the inherent symmetries of the vector fields. …

On Invariance, Equivariance, Correlation and Convolution of Spherical Harmonic Representations for Scalar and Vectorial Data

2023-07-06 · Janis Keuper

The mathematical representations of data in the Spherical Harmonic (SH) domain has recently regained increasing interest in the machine learning community. This technical report gives an in-depth introduction to the theo…