skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Interaction Networks for the Identification of Boosted $$H\to b\overline{b}$$ Decays

Abstract

We develop a jet identification algorithm based on an interaction network, designed to identify high-momentum Higgs bosons decaying to bottom quark-antiquark pairs, distinguish them from ordinary jets originating from the hadronization of quarks and gluons. The algorithm's inputs are features of the reconstructed charged particles in a jet and the secondary vertices associated to them. Describing the jet shower as a combination of particle-to-particle and particle-to-vertex interactions, the model is trained to learn a jet representation on which the classification problem is optimized. The algorithm is trained on simulated samples of accurate LHC collisions, released by the CMS collaboration on the CERN Open Data Portal. The interaction network achieves a drastic improvement in the identification performance with respect to state-of-the-art algorithms.

Authors:
 [1];  [1];  [1];  [1];  [1];  [1];  [1];  [2];  [3]
  1. Caltech
  2. Fermilab
  3. CERN
Publication Date:
Research Org.:
Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
Sponsoring Org.:
USDOE Office of Science (SC), High Energy Physics (HEP) (SC-25)
OSTI Identifier:
1571809
Report Number(s):
arXiv:1909.12285; FERMILAB-PUB-19-492-CMS-E
oai:inspirehep.net:1756269
DOE Contract Number:  
AC02-07CH11359
Resource Type:
Journal Article
Journal Name:
TBD
Additional Journal Information:
Journal Name: TBD
Country of Publication:
United States
Language:
English
Subject:
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS

Citation Formats

Moreno, Eric A., Nguyen, Thong Q., Vlimant, Jean-Roch, Cerri, Olmo, Newman, Harvey B., Periwal, Avikar, Spiropulu, Maria, Duarte, Javier M., and Pierini, Maurizio. Interaction Networks for the Identification of Boosted $H\to b\overline{b}$ Decays. United States: N. p., 2019. Web.
Moreno, Eric A., Nguyen, Thong Q., Vlimant, Jean-Roch, Cerri, Olmo, Newman, Harvey B., Periwal, Avikar, Spiropulu, Maria, Duarte, Javier M., & Pierini, Maurizio. Interaction Networks for the Identification of Boosted $H\to b\overline{b}$ Decays. United States.
Moreno, Eric A., Nguyen, Thong Q., Vlimant, Jean-Roch, Cerri, Olmo, Newman, Harvey B., Periwal, Avikar, Spiropulu, Maria, Duarte, Javier M., and Pierini, Maurizio. Thu . "Interaction Networks for the Identification of Boosted $H\to b\overline{b}$ Decays". United States. https://www.osti.gov/servlets/purl/1571809.
@article{osti_1571809,
title = {Interaction Networks for the Identification of Boosted $H\to b\overline{b}$ Decays},
author = {Moreno, Eric A. and Nguyen, Thong Q. and Vlimant, Jean-Roch and Cerri, Olmo and Newman, Harvey B. and Periwal, Avikar and Spiropulu, Maria and Duarte, Javier M. and Pierini, Maurizio},
abstractNote = {We develop a jet identification algorithm based on an interaction network, designed to identify high-momentum Higgs bosons decaying to bottom quark-antiquark pairs, distinguish them from ordinary jets originating from the hadronization of quarks and gluons. The algorithm's inputs are features of the reconstructed charged particles in a jet and the secondary vertices associated to them. Describing the jet shower as a combination of particle-to-particle and particle-to-vertex interactions, the model is trained to learn a jet representation on which the classification problem is optimized. The algorithm is trained on simulated samples of accurate LHC collisions, released by the CMS collaboration on the CERN Open Data Portal. The interaction network achieves a drastic improvement in the identification performance with respect to state-of-the-art algorithms.},
doi = {},
journal = {TBD},
number = ,
volume = ,
place = {United States},
year = {2019},
month = {9}
}