Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Spinner, Jonas, Bresó, Victor, de Haan, Pim, Plehn, Tilman, Thaler, Jesse, Brehmer, Johann
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915348581711872
author Spinner, Jonas
Bresó, Victor
de Haan, Pim
Plehn, Tilman
Thaler, Jesse
Brehmer, Johann
author_facet Spinner, Jonas
Bresó, Victor
de Haan, Pim
Plehn, Tilman
Thaler, Jesse
Brehmer, Johann
contents Extracting scientific understanding from particle-physics experiments requires solving diverse learning problems with high precision and good data efficiency. We propose the Lorentz Geometric Algebra Transformer (L-GATr), a new multi-purpose architecture for high-energy physics. L-GATr represents high-energy data in a geometric algebra over four-dimensional space-time and is equivariant under Lorentz transformations, the symmetry group of relativistic kinematics. At the same time, the architecture is a Transformer, which makes it versatile and scalable to large systems. L-GATr is first demonstrated on regression and classification tasks from particle physics. We then construct the first Lorentz-equivariant generative model: a continuous normalizing flow based on an L-GATr network, trained with Riemannian flow matching. Across our experiments, L-GATr is on par with or outperforms strong domain-specific baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14806
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics
Spinner, Jonas
Bresó, Victor
de Haan, Pim
Plehn, Tilman
Thaler, Jesse
Brehmer, Johann
Data Analysis, Statistics and Probability
Machine Learning
High Energy Physics - Phenomenology
Extracting scientific understanding from particle-physics experiments requires solving diverse learning problems with high precision and good data efficiency. We propose the Lorentz Geometric Algebra Transformer (L-GATr), a new multi-purpose architecture for high-energy physics. L-GATr represents high-energy data in a geometric algebra over four-dimensional space-time and is equivariant under Lorentz transformations, the symmetry group of relativistic kinematics. At the same time, the architecture is a Transformer, which makes it versatile and scalable to large systems. L-GATr is first demonstrated on regression and classification tasks from particle physics. We then construct the first Lorentz-equivariant generative model: a continuous normalizing flow based on an L-GATr network, trained with Riemannian flow matching. Across our experiments, L-GATr is on par with or outperforms strong domain-specific baselines.
title Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics
topic Data Analysis, Statistics and Probability
Machine Learning
High Energy Physics - Phenomenology
url https://arxiv.org/abs/2405.14806