Symmetries, Safety, and Self-Supervision

Collider searches face the challenge of defining a representation of high-dimensional data such that physical symmetries are manifest, the discriminating features are retained, and the choice of representation is new-physics agnostic. We introduce JetCLR to solve the mapping from low-level data to o...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Dillon, Barry M, Kasieczka, Gregor, Olischlager, Hans, Plehn, Tilman, Sorrenson, Peter, Vogel, Lorenz
Format Paper Journal Article
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 09.08.2021
Subjects
Coders
Permutations
Physics - High Energy Physics - Phenomenology
Quantum chromodynamics
Representations
Online AccessGet full text

Cover

More Information
Summary:Collider searches face the challenge of defining a representation of high-dimensional data such that physical symmetries are manifest, the discriminating features are retained, and the choice of representation is new-physics agnostic. We introduce JetCLR to solve the mapping from low-level data to optimized observables though self-supervised contrastive learning. As an example, we construct a data representation for top and QCD jets using a permutation-invariant transformer-encoder network and visualize its symmetry properties. We compare the JetCLR representation with alternative representations using linear classifier tests and find it to work quite well.
ISSN:2331-8422
DOI:10.48550/arxiv.2108.04253