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...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
9 June 2022
|
| In: |
SciPost physics
Year: 2022, Volume: 12, Issue: 6, Pages: 1-19 |
| ISSN: | 2542-4653 |
| DOI: | 10.21468/SciPostPhys.12.6.188 |
| Online Access: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.21468/SciPostPhys.12.6.188 Verlag, lizenzpflichtig, Volltext: https://scipost.org/10.21468/SciPostPhys.12.6.188 
|
| Author Notes: | Barry Dillon, Gregor Kasieczka, Hans Olischlager, Tilman Plehn, Peter Sorrenson and Lorenz Vogel |
| 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. |
|---|---|
| Item Description: | Gesehen am 14.07.2022 |
| Physical Description: | Online Resource |
| ISSN: | 2542-4653 |
| DOI: | 10.21468/SciPostPhys.12.6.188 |