Journal
SCIPOST PHYSICS
Volume 12, Issue 6, Pages -Publisher
SCIPOST FOUNDATION
DOI: 10.21468/SciPostPhys.12.6.188
Keywords
-
Categories
Funding
- Deutsche Forschungsgemeinschaft [396021762 - TRR 257]
- DFG Research Training Group [GK-1940]
- BMBF
- Deutsche Forschungsgemeinschaft under Germany's Excellence Strategy [390833306, EXC 2121]
- Wissenschaftsministerium Baden-Wurttemberg through the Excellence Strategy
Ask authors/readers for more resources
This paper introduces the JetCLR method to solve the mapping problem from low-level data to optimized observables through self-supervised contrastive learning. A symmetric data representation is constructed using a permutation-invariant transformer-encoder network for top and QCD jets, and its performance is compared with alternative representations using linear classifier tests, showing good results.
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 through 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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available