skip to main content

DOE PAGESDOE PAGES

Title: Pileup Mitigation with Machine Learning (PUMML)

Pileup involves the contamination of the energy distribution arising from the primary collision of interest (leading vertex) by radiation from soft collisions (pileup). We develop a new technique for removing this contamination using machine learning and convolutional neural networks. The network takes as input the energy distribution of charged leading vertex particles, charged pileup particles, and all neutral particles and outputs the energy distribution of particles coming from leading vertex alone. The PUMML algorithm performs remarkably well at eliminating pileup distortion on a wide range of simple and complex jet observables. We test the robustness of the algorithm in a number of ways and discuss how the network can be trained directly on data.
Authors:
 [1] ;  [1] ;  [2] ;  [3]
  1. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
  2. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
  3. Harvard Univ., Cambridge, MA (United States)
Publication Date:
Grant/Contract Number:
AC02-05CH11231; SC0013607; SC0011090; SC0012567
Type:
Accepted Manuscript
Journal Name:
Journal of High Energy Physics (Online)
Additional Journal Information:
Journal Name: Journal of High Energy Physics (Online); Journal Volume: 2017; Journal Issue: 12; Journal ID: ISSN 1029-8479
Publisher:
Springer Berlin
Research Org:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org:
USDOE Office of Science (SC), High Energy Physics (HEP) (SC-25); USDOE Office of Science (SC), Nuclear Physics (NP) (SC-26)
Country of Publication:
United States
Language:
English
Subject:
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS; Jets
OSTI Identifier:
1485069

Komiske, Patrick T., Metodiev, Eric M., Nachman, Benjamin, and Schwartz, Matthew D.. Pileup Mitigation with Machine Learning (PUMML). United States: N. p., Web. doi:10.1007/jhep12(2017)051.
Komiske, Patrick T., Metodiev, Eric M., Nachman, Benjamin, & Schwartz, Matthew D.. Pileup Mitigation with Machine Learning (PUMML). United States. doi:10.1007/jhep12(2017)051.
Komiske, Patrick T., Metodiev, Eric M., Nachman, Benjamin, and Schwartz, Matthew D.. 2017. "Pileup Mitigation with Machine Learning (PUMML)". United States. doi:10.1007/jhep12(2017)051. https://www.osti.gov/servlets/purl/1485069.
@article{osti_1485069,
title = {Pileup Mitigation with Machine Learning (PUMML)},
author = {Komiske, Patrick T. and Metodiev, Eric M. and Nachman, Benjamin and Schwartz, Matthew D.},
abstractNote = {Pileup involves the contamination of the energy distribution arising from the primary collision of interest (leading vertex) by radiation from soft collisions (pileup). We develop a new technique for removing this contamination using machine learning and convolutional neural networks. The network takes as input the energy distribution of charged leading vertex particles, charged pileup particles, and all neutral particles and outputs the energy distribution of particles coming from leading vertex alone. The PUMML algorithm performs remarkably well at eliminating pileup distortion on a wide range of simple and complex jet observables. We test the robustness of the algorithm in a number of ways and discuss how the network can be trained directly on data.},
doi = {10.1007/jhep12(2017)051},
journal = {Journal of High Energy Physics (Online)},
number = 12,
volume = 2017,
place = {United States},
year = {2017},
month = {12}
}