Mass agnostic jet taggers
- Univ. of Oregon, Eugene, OR (United States). Dept. of Physics. Center for High Energy Physics. Inst. of Theoretical Science
- Scuola Normale Superiore (SNS), Pisa (Italy). Istituto Nazionale di Fisica Nucleare (INFN)
- Univ. of Oregon, Eugene, OR (United States). Dept. of Physics. Center for High Energy Physics. Inst. of Theoretical Science
Searching for new physics in large data sets needs a balance between two competing effects---signal identification vs background distortion. In this work, we perform a systematic study of both single variable and multivariate jet tagging methods that aim for this balance. The methods preserve the shape of the background distribution by either augmenting the training procedure or the data itself. Multiple quantitative metrics to compare the methods are considered, for tagging 2-, 3-, or 4-prong jets from the QCD background. This is the first study to show that the data augmentation techniques of Planing and PCA based scaling deliver similar performance as the augmented training techniques of Adversarial NN and uBoost, but are both easier to implement and computationally cheaper.
- Research Organization:
- Univ. of Oregon, Eugene, OR (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC)
- Grant/Contract Number:
- SC0011640
- OSTI ID:
- 1594194
- Alternate ID(s):
- OSTI ID: 1802234; OSTI ID: 1905954
- Journal Information:
- SciPost Physics, Vol. 8, Issue 1; ISSN 2542-4653
- Publisher:
- SciPost FoundationCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Web of Science
Similar Records
Do graph neural networks learn traditional jet substructure?
Performance and calibration of quark/gluon-jet taggers using 140 fb–1 of pp collisions at $\sqrt{s}$ = 13 TeV with the ATLAS detector