A Lorentz-Equivariant Transformer for All of the LHC

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Brehmer, Johann, Bresó, Víctor, de Haan, Pim, Plehn, Tilman, Qu, Huilin, Spinner, Jonas, Thaler, Jesse
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917048276221952
author Brehmer, Johann
Bresó, Víctor
de Haan, Pim
Plehn, Tilman
Qu, Huilin
Spinner, Jonas
Thaler, Jesse
author_facet Brehmer, Johann
Bresó, Víctor
de Haan, Pim
Plehn, Tilman
Qu, Huilin
Spinner, Jonas
Thaler, Jesse
contents We show that the Lorentz-Equivariant Geometric Algebra Transformer (L-GATr) yields state-of-the-art performance for a wide range of machine learning tasks at the Large Hadron Collider. L-GATr represents data in a geometric algebra over space-time and is equivariant under Lorentz transformations. The underlying architecture is a versatile and scalable transformer, which is able to break symmetries if needed. We demonstrate the power of L-GATr for amplitude regression and jet classification, and then benchmark it as the first Lorentz-equivariant generative network. For all three LHC tasks, we find significant improvements over previous architectures.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00446
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Lorentz-Equivariant Transformer for All of the LHC
Brehmer, Johann
Bresó, Víctor
de Haan, Pim
Plehn, Tilman
Qu, Huilin
Spinner, Jonas
Thaler, Jesse
High Energy Physics - Phenomenology
Machine Learning
High Energy Physics - Experiment
We show that the Lorentz-Equivariant Geometric Algebra Transformer (L-GATr) yields state-of-the-art performance for a wide range of machine learning tasks at the Large Hadron Collider. L-GATr represents data in a geometric algebra over space-time and is equivariant under Lorentz transformations. The underlying architecture is a versatile and scalable transformer, which is able to break symmetries if needed. We demonstrate the power of L-GATr for amplitude regression and jet classification, and then benchmark it as the first Lorentz-equivariant generative network. For all three LHC tasks, we find significant improvements over previous architectures.
title A Lorentz-Equivariant Transformer for All of the LHC
topic High Energy Physics - Phenomenology
Machine Learning
High Energy Physics - Experiment
url https://arxiv.org/abs/2411.00446