Exploring End-to-end Deep Learning Applications for Event Classification at CMS

Andrews, Michael; Paulini, Manfred; Gleyzer, Sergei; Poczos, Barnabas

doi:10.1051/epjconf/201921406031

Title: Exploring End-to-end Deep Learning Applications for Event Classification at CMS

Abstract

An essential part of new physics searches at the Large Hadron Collider (LHC) at CERN involves event classification, or distinguishing potential signal events from those coming from background processes. Current machine learning techniques accomplish this using traditional hand-engineered features like particle 4-momenta, motivated by our understanding of particle decay phenomenology. While such techniques have proven useful for simple decays, they are highly dependent on our ability to model all aspects of the phenomenology and detector response. Meanwhile, powerful deep learning algorithms are capable of not only training on high-level features, but of performing feature extraction. In computer vision, convolutional neural networks have become the state-of-the-art for many applications. Motivated by their success, we apply deep learning algorithms to low-level detector data from the 2012 CMS Simulated Open Data to directly learn useful features, in what we call, end-to-end event classification. We demonstrate the power of this approach in the context of a physics search and offer solutions to some of the inherent challenges, such as image construction, image sparsity, combining multiple sub-detectors, and de-correlating the classifier from the search observable, among others.

Authors:

Andrews, Michael ^[1]; Paulini, Manfred ^[1]; Gleyzer, Sergei ^[2]; Poczos, Barnabas ^[1]

Carnegie Mellon Univ., Pittsburgh, PA (United States)
Univ. of Florida, Gainesville, FL (United States)

Publication Date:: 2019-09-17

Research Org.:: Carnegie Mellon Univ., Pittsburgh, PA (United States)

Sponsoring Org.:: USDOE Office of Science (SC), High Energy Physics (HEP)

OSTI Identifier:: 1755630

Grant/Contract Number:: SC0010118

Resource Type:: Accepted Manuscript

Journal Name:: EPJ Web of Conferences (Online)

Additional Journal Information:: Journal Name: EPJ Web of Conferences (Online); Journal Volume: 214; Journal ID: ISSN 2100-014X

Publisher:: EDP Sciences

Country of Publication:: United States

Language:: English

Subject:: 72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS

Citation Formats


                    Andrews, Michael, Paulini, Manfred, Gleyzer, Sergei, and Poczos, Barnabas. Exploring End-to-end Deep Learning Applications for Event Classification at CMS.  United States: N. p., 2019. 
Web.  doi:10.1051/epjconf/201921406031.

Copy to clipboard


                    Andrews, Michael, Paulini, Manfred, Gleyzer, Sergei, & Poczos, Barnabas. Exploring End-to-end Deep Learning Applications for Event Classification at CMS.  United States.  https://doi.org/10.1051/epjconf/201921406031

Copy to clipboard


                    Andrews, Michael, Paulini, Manfred, Gleyzer, Sergei, and Poczos, Barnabas. Tue .  
"Exploring End-to-end Deep Learning Applications for Event Classification at CMS".  United States.  https://doi.org/10.1051/epjconf/201921406031.  https://www.osti.gov/servlets/purl/1755630.

Copy to clipboard


                    
@article{osti_1755630,

  title        = {Exploring End-to-end Deep Learning Applications for Event Classification at CMS},

  author       = {Andrews, Michael and Paulini, Manfred and Gleyzer, Sergei and Poczos, Barnabas},

  abstractNote = {An essential part of new physics searches at the Large Hadron Collider (LHC) at CERN involves event classification, or distinguishing potential signal events from those coming from background processes. Current machine learning techniques accomplish this using traditional hand-engineered features like particle 4-momenta, motivated by our understanding of particle decay phenomenology. While such techniques have proven useful for simple decays, they are highly dependent on our ability to model all aspects of the phenomenology and detector response. Meanwhile, powerful deep learning algorithms are capable of not only training on high-level features, but of performing feature extraction. In computer vision, convolutional neural networks have become the state-of-the-art for many applications. Motivated by their success, we apply deep learning algorithms to low-level detector data from the 2012 CMS Simulated Open Data to directly learn useful features, in what we call, end-to-end event classification. We demonstrate the power of this approach in the context of a physics search and offer solutions to some of the inherent challenges, such as image construction, image sparsity, combining multiple sub-detectors, and de-correlating the classifier from the search observable, among others.},

  doi          = {10.1051/epjconf/201921406031},

  journal      = {EPJ Web of Conferences (Online)},

  number       = ,

  volume       = 214,

  place        = {United States},

  year         = {2019},

  month        = {9}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1051/epjconf/201921406031

Other availability

Search WorldCat to find libraries that may hold this journal

Save / Share:

Export Metadata

Save to My Library

Works referenced in this record:

Searching for exotic particles in high-energy physics with deep learning
journal, July 2014

Baldi, P.; Sadowski, P.; Whiteson, D.
Nature Communications, Vol. 5, Issue 1
DOI: 10.1038/ncomms5308

Jet-images: computer vision inspired techniques for jet tagging
journal, February 2015

Cogan, Josh; Kagan, Michael; Strauss, Emanuel
Journal of High Energy Physics, Vol. 2015, Issue 2
DOI: 10.1007/JHEP02(2015)118

New approaches for boosting to uniformity
journal, March 2015

Rogozhnikov, A.; Bukva, A.; Gligorov, V.
Journal of Instrumentation, Vol. 10, Issue 03
DOI: 10.1088/1748-0221/10/03/T03002

Observation of the diphoton decay of the Higgs boson and measurement of its properties
journal, October 2014

Khachatryan, V.; Sirunyan, A. M.; Tumasyan, A.
The European Physical Journal C, Vol. 74, Issue 10
DOI: 10.1140/epjc/s10052-014-3076-z

Jet-images — deep learning edition
journal, July 2016

de Oliveira, Luke; Kagan, Michael; Mackey, Lester
Journal of High Energy Physics, Vol. 2016, Issue 7
DOI: 10.1007/JHEP07(2016)069

Deep-learning top taggers or the end of QCD?
journal, May 2017

Kasieczka, Gregor; Plehn, Tilman; Russell, Michael
Journal of High Energy Physics, Vol. 2017, Issue 5
DOI: 10.1007/JHEP05(2017)006

Deep learning in color: towards automated quark/gluon jet discrimination
journal, January 2017

Komiske, Patrick T.; Metodiev, Eric M.; Schwartz, Matthew D.
Journal of High Energy Physics, Vol. 2017, Issue 1
DOI: 10.1007/JHEP01(2017)110

Particle-flow reconstruction and global event description with the CMS detector
journal, October 2017

Sirunyan, A. M.; Tumasyan, A.; Adam, W.
Journal of Instrumentation, Vol. 12, Issue 10
DOI: 10.1088/1748-0221/12/10/P10003

A convolutional neural network neutrino event classifier
journal, September 2016

Aurisano, A.; Radovic, A.; Rocco, D.
Journal of Instrumentation, Vol. 11, Issue 09
DOI: 10.1088/1748-0221/11/09/P09001

Works referencing / citing this record:

Invisible Higgs search through vector boson fusion: a deep learning approach
journal, November 2020

Ngairangbam, Vishal S.; Bhardwaj, Akanksha; Konar, Partha
The European Physical Journal C, Vol. 80, Issue 11
DOI: 10.1140/epjc/s10052-020-08629-w

Similar Records in DOE PAGES and OSTI.GOV collections:

End-to-End Event Classification of High-Energy Physics Data

Journal Article Andrews, M. ; Paulini, M. ; Gleyzer, S. ; ... - Journal of Physics. Conference Series

Feature extraction algorithms, such as convolutional neural networks, have introduced the possibility of using deep learning to train directly on raw data without the need for rule-based feature engineering. In the context of particle physics, such end-to-end approaches can be used for event classification to learn directly from detector-level data in a way that is completely independent of the high-level physics reconstruction. We demonstrate a technique for building such end-to-end event classifiers to distinguish simulated electromagnetic decays in a high-fidelity model of the CMS Electromagnetic Calorimeter.
https://doi.org/10.1088/1742-6596/1085/4/042022

Full Text Available
End-to-end jet classification of quarks and gluons with the CMS Open Data

Journal Article Andrews, M. ; Alison, J. ; An, S. ; ... - Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment

We describe the construction of novel end-to-end jet image classifiers to discriminate quark- versus gluon-initiated jets using the simulated CMS Open Data. These multi-detector images correspond to true maps of the low-level energy deposits in the detector, giving the classifiers direct access to the maximum recorded event information about the jet, differing fundamentally from conventional jet images constructed from reconstructed particle-level information. Using this approach, we achieve classification performance competitive with current state-of-the-art jet classifiers that are dominated by particle-based algorithms. We find the performance to be driven by the availability of precise spatial information, highlighting the importance of high-fidelitymore »« less
https://doi.org/10.1016/j.nima.2020.164304
End-to-End Physics Event Classification with CMS Open Data: Applying Image-Based Deep Learning to Detector Data for the Direct Classification of Collision Events at the LHC

Journal Article Andrews, M. ; Paulini, M. ; Gleyzer, S. ; ... - Computing and Software for Big Science

This paper describes the construction of novel end-to-end image-based classifiers that directly leverage low-level simulated detector data to discriminate signal and background processes in pp collision events at the Large Hadron Collider at CERN. To better understand what end-to-end classifiers are capable of learning from the data and to address a number of associated challenges, we distinguish the decay of the standard model Higgs boson into two photons from its leading background sources using high-fidelity simulated CMS Open Data. We demonstrate the ability of end-to-end classifiers to learn from the angular distribution of the photons recorded as electromagnetic showers, theirmore »« less
https://doi.org/10.1007/s41781-020-00038-8

Full Text Available
Accelerating End-to-End Deep Learning for Particle Reconstruction using CMS open data

Journal Article Andrews, Michael ; Burkle, Bjorn ; Chaudhari, Shravan ; ... - EPJ Web of Conferences (Online)

Machine learning algorithms are gaining ground in high energy physics for applications in particle and event identification, physics analysis, detector reconstruction, simulation and trigger. Currently, most data-analysis tasks at LHC experiments benefit from the use of machine learning. Incorporating these computational tools in the experimental framework presents new challenges. This paper reports on the implementation of the end-to-end deep learning with the CMS software framework and the scaling of the end-to-end deep learning with multiple GPUs. The end-to-end deep learning technique combines deep learning algorithms and low-level detector representation for particle and event identification. We demonstrate the end-to-end implementation onmore »« less
https://doi.org/10.1051/epjconf/202125103057

Full Text Available
End-to-End Jet Classification of Boosted Top Quarks with CMS Open Data

Journal Article Andrews, Michael ; Burkle, Bjorn ; Chaudhari, Shravan ; ... - EPJ Web of Conferences (Online)

We describe a novel application of the end-to-end deep learning technique to the task of discriminating top quark-initiated jets from those originating from the hadronization of a light quark or a gluon. The end-to-end deep learning technique combines deep learning algorithms and low-level detector representation of the high-energy collision event. In this study, we use lowlevel detector information from the simulated CMS Open Data samples to construct the top jet classifiers. To optimize classifier performance we progressively add low-level information from the CMS tracking detector, including pixel detector reconstructed hits and impact parameters, and demonstrate the value of additional trackingmore »« less
https://doi.org/10.1051/epjconf/202125104030

Full Text Available

Similar Records

Title: Exploring End-to-end Deep Learning Applications for Event Classification at CMS

Abstract

Citation Formats

Searching for exotic particles in high-energy physics with deep learning journal, July 2014

Jet-images: computer vision inspired techniques for jet tagging journal, February 2015

New approaches for boosting to uniformity journal, March 2015

Observation of the diphoton decay of the Higgs boson and measurement of its properties journal, October 2014

Jet-images — deep learning edition journal, July 2016

Deep-learning top taggers or the end of QCD? journal, May 2017

Deep learning in color: towards automated quark/gluon jet discrimination journal, January 2017

Particle-flow reconstruction and global event description with the CMS detector journal, October 2017

A convolutional neural network neutrino event classifier journal, September 2016

Invisible Higgs search through vector boson fusion: a deep learning approach journal, November 2020

Searching for exotic particles in high-energy physics with deep learning
journal, July 2014

Jet-images: computer vision inspired techniques for jet tagging
journal, February 2015

New approaches for boosting to uniformity
journal, March 2015

Observation of the diphoton decay of the Higgs boson and measurement of its properties
journal, October 2014

Jet-images — deep learning edition
journal, July 2016

Deep-learning top taggers or the end of QCD?
journal, May 2017

Deep learning in color: towards automated quark/gluon jet discrimination
journal, January 2017

Particle-flow reconstruction and global event description with the CMS detector
journal, October 2017

A convolutional neural network neutrino event classifier
journal, September 2016

Invisible Higgs search through vector boson fusion: a deep learning approach
journal, November 2020