Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Enhancing searches for resonances with machine learning and moment decomposition

Journal Article · · Journal of High Energy Physics (Online)
 [1];  [2];  [1];  [3]
  1. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States); The NSF AI Institute for Artificial Intelligence and Fundamental Interactions, Cambridge, MA (United States)
  2. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Univ. of California, Berkeley, CA (United States)
  3. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States); The NSF AI Institute for Artificial Intelligence and Fundamental Interactions, Cambridge, MA (United States); Monash Univ., Melbourne, VIC (Australia)
+ Show Author Affiliations

A key challenge in searches for resonant new physics is that classifiers trained to enhance potential signals must not induce localized structures. Such structures could result in a false signal when the background is estimated from data using sideband methods. A variety of techniques have been developed to construct classifiers which are independent from the resonant feature (often a mass). Such strategies are sufficient to avoid localized structures, but are not necessary. We develop a new set of tools using a novel moment loss function (Moment Decomposition or MoDe) which relax the assumption of independence without creating structures in the background. Here, by allowing classifiers to be more flexible, we enhance the sensitivity to new physics without compromising the fidelity of the background estimation.

Research Organization:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
Sponsoring Organization:
USDOE Office of Science (SC), High Energy Physics (HEP); National Science Foundation
Grant/Contract Number:
AC02-05CH11231
OSTI ID:
1820596
Journal Information:
Journal of High Energy Physics (Online), Journal Name: Journal of High Energy Physics (Online) Journal Issue: 4 Vol. 2021; ISSN 1029-8479
Publisher:
Springer NatureCopyright Statement
Country of Publication:
United States
Language:
English

References (44)

DELPHES 3: A modular framework for fast-simulation of generic collider experiments journal June 2014
DELPHES 3: a modular framework for fast simulation of a generic collider experiment journal February 2014
Identifying boosted objects with N-subjettiness journal March 2011
Thinking outside the ROCs: Designing Decorrelated Taggers (DDT) for jet substructure journal May 2016
Convolved substructure: analytically decorrelating jet substructure observables journal May 2018
Jet-images — deep learning edition journal July 2016
Power counting to better jet observables journal December 2014
Reducing the Dependence of the Neural Network Function to Systematic Uncertainties in the Input Space journal February 2020
Longitudinally-invariant k⊥-clustering algorithms for hadron-hadron collisions journal September 1993
An introduction to PYTHIA 8.2 journal June 2015
The distance correlation t -test of independence in high dimension journal May 2013
QBDT, a new boosting decision tree method with systematical uncertainties into training for High Energy Physics journal June 2019
Jet substructure at the Large Hadron Collider: A review of recent advances in theory and machine learning journal November 2019
Machine learning at the energy and intensity frontiers of particle physics journal August 2018
PYTHIA 6.4 physics and manual journal May 2006
The anti- k t jet clustering algorithm journal April 2008
Strategies to identify boosted tops journal July 2008
Machine Learning in High Energy Physics Community White Paper journal September 2018
New features in Delphes 3 journal May 2015
New approaches for boosting to uniformity journal March 2015
uBoost: a boosting method for producing uniform selection efficiencies from multivariate classifiers journal December 2013
A deep neural network to search for new long-lived particles decaying to jets journal August 2020
Pion-Pion Interaction in the Reaction p ¯ + p → 2 π + + 2 π − + n π 0 journal June 1962
Automating the ABCD method with machine learning journal February 2021
Top quark jets at the LHC journal April 2009
New approach to identifying boosted hadronically decaying particles using jet substructure in its center-of-mass frame journal February 2012
Search for baryon-number and lepton-number violating decays of Λ hyperons using the CLAS detector at Jefferson Laboratory journal October 2015
Decorrelated jet substructure tagging using adversarial neural networks journal October 2017
What is the machine learning? journal March 2018
Robust Jet Classifiers through Distance Correlation journal September 2020
Observables for the Analysis of Event Shapes in e + e − Annihilation and Other Processes journal December 1978
FastJet user manual: (for version 3.0.2) journal March 2012
Machine learning uncertainties with adversarial neural networks journal January 2019
Machine and deep learning applications in particle physics journal December 2019
Deep Learning and Its Application to LHC Physics journal October 2018
Measuring and testing dependence by correlation of distances journal December 2007
Partial distance correlation with methods for dissimilarities journal December 2014
ATLAS measurements of the properties of jets for boosted particle searches collection January 2012
Search for heavy resonances decaying into two Higgs bosons or into a Higgs boson and a W or Z boson in proton-proton collisions at 13 TeV collection January 2019
Combination of CMS searches for heavy resonances decaying to pairs of bosons or leptons collection January 2020
Pair invariant mass to isolate background in the search for the chiral magnetic effect in Au+Au collisions at $\sqrt{s_{_{\rm NN}}}$= 200 GeV collection January 2022
Mass agnostic jet taggers journal January 2020
Datasets for Boosted W Tagging dataset January 2020
Datasets for Boosted W Tagging dataset January 2020

Similar Records

Related Subjects

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS
Jets