Neural embedding: learning the embedding of the manifold of physics data

Park, Sang Eon; Harris, Philip; Ostdiek, Bryan

doi:10.1007/jhep07(2023)108

Neural embedding: learning the embedding of the manifold of physics data

Journal Article · Wed Jul 12 00:00:00 EDT 2023 · Journal of High Energy Physics (Online)

DOI:https://doi.org/10.1007/jhep07(2023)108· OSTI ID:2421813

^[1]; Harris, Philip ^[2]; Ostdiek, Bryan ^[3]

Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States); National Science Foundation (NSF), Cambridge, MA (United States). AI Institute for Artificial Intelligence and Fundamental Interactions; Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States); National Science Foundation (NSF), Cambridge, MA (United States). AI Institute for Artificial Intelligence and Fundamental Interactions
Harvard Univ., Cambridge, MA (United States); National Science Foundation (NSF), Cambridge, MA (United States). AI Institute for Artificial Intelligence and Fundamental Interactions

In this paper, we present a method of embedding physics data manifolds with metric structure into lower dimensional spaces with simpler metrics, such as Euclidean and Hyperbolic spaces. We then demonstrate that it can be a powerful step in the data analysis pipeline for many applications. Using progressively more realistic simulated collisions at the Large Hadron Collider, we show that this embedding approach learns the underlying latent structure. With the notion of volume in Euclidean spaces, we provide for the first time a viable solution to quantifying the true search capability of model agnostic search algorithms in collider physics (i.e. anomaly detection). Finally, we discuss how the ideas presented in this paper can be employed to solve many practical challenges that require the extraction of physically meaningful representations from information in complex high dimensional datasets.

View Accepted Manuscript (DOE)

Research Organization:: Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)

Sponsoring Organization:: USDOE Office of Science (SC)

Grant/Contract Number:: SC0021225; SC0021943

OSTI ID:: 2421813

Journal Information:: Journal of High Energy Physics (Online), Journal Name: Journal of High Energy Physics (Online) Journal Issue: 7 Vol. 2023; ISSN 1029-8479

Publisher:: Springer NatureCopyright Statement

Country of Publication:: United States

Language:: English

References (43)

RanBox: anomaly detection in the copula space Dorigo, Tommaso; Fumanelli, Martina; Maccani, Chiara Journal of High Energy Physics, Vol. 2023, Issue 1 https://doi.org/10.1007/JHEP01(2023)008	journal	January 2023
DELPHES 3: a modular framework for fast simulation of a generic collider experiment de Favereau, J.; Delaere, C.; Demin, P. Journal of High Energy Physics, Vol. 2014, Issue 2 https://doi.org/10.1007/JHEP02(2014)057	journal	February 2014
Quantum anomaly detection for collider physics Alvi, Sulaiman; Bauer, Christian W.; Nachman, Benjamin Journal of High Energy Physics, Vol. 2023, Issue 2 https://doi.org/10.1007/JHEP02(2023)220	journal	February 2023
Challenges for unsupervised anomaly detection in particle physics Fraser, Katherine; Homiller, Samuel; Mishra, Rashmish K. Journal of High Energy Physics, Vol. 2022, Issue 3 https://doi.org/10.1007/JHEP03(2022)066	journal	March 2022
Variational autoencoders for new physics mining at the Large Hadron Collider Cerri, Olmo; Nguyen, Thong Q.; Pierini, Maurizio Journal of High Energy Physics, Vol. 2019, Issue 5 https://doi.org/10.1007/JHEP05(2019)036	journal	May 2019
Autoencoders for unsupervised anomaly detection in high energy physics Finke, Thorben; Krämer, Michael; Morandini, Alessandro Journal of High Energy Physics, Vol. 2021, Issue 6 https://doi.org/10.1007/JHEP06(2021)161	journal	June 2021
The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations Alwall, J.; Frederix, R.; Frixione, S. Journal of High Energy Physics, Vol. 2014, Issue 7 https://doi.org/10.1007/JHEP07(2014)079	journal	July 2014
Anomaly detection with convolutional Graph Neural Networks Atkinson, Oliver; Bhardwaj, Akanksha; Englert, Christoph Journal of High Energy Physics, Vol. 2021, Issue 8 https://doi.org/10.1007/JHEP08(2021)080	journal	August 2021
Classification without labels: learning from mixed samples in high energy physics Metodiev, Eric M.; Nachman, Benjamin; Thaler, Jesse Journal of High Energy Physics, Vol. 2017, Issue 10 https://doi.org/10.1007/JHEP10(2017)174	journal	October 2017
Adversarially-trained autoencoders for robust unsupervised new physics searches Blance, Andrew; Spannowsky, Michael; Waite, Philip Journal of High Energy Physics, Vol. 2019, Issue 10 https://doi.org/10.1007/JHEP10(2019)047	journal	October 2019
SMR: Medical Knowledge Graph Embedding for Safe Medicine Recommendation Gong, Fan; Wang, Meng; Wang, Haofen Big Data Research, Vol. 23 https://doi.org/10.1016/j.bdr.2020.100174	journal	February 2021
A visual embedding for the unsupervised extraction of abstract semantics Garcia-Gasulla, D.; Ayguadé, E.; Labarta, J. Cognitive Systems Research, Vol. 42 https://doi.org/10.1016/j.cogsys.2016.11.008	journal	May 2017
An introduction to PYTHIA 8.2 Sjöstrand, Torbjörn; Ask, Stefan; Christiansen, Jesper R. Computer Physics Communications, Vol. 191 https://doi.org/10.1016/j.cpc.2015.01.024	journal	June 2015
WordNet2Vec: Corpora agnostic word vectorization method Bartusiak, Roman; Augustyniak, Łukasz; Kajdanowicz, Tomasz Neurocomputing, Vol. 326-327 https://doi.org/10.1016/j.neucom.2017.01.121	journal	January 2019
Dispelling the N3 myth for the kt jet-finder Cacciari, Matteo; Salam, Gavin P. Physics Letters B, Vol. 641, Issue 1 https://doi.org/10.1016/j.physletb.2006.08.037	journal	September 2006
Poincaré maps for analyzing complex hierarchies in single-cell data Klimovskaia, Anna; Lopez-Paz, David; Bottou, Léon Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-020-16822-4	journal	June 2020
The anti- k _t jet clustering algorithm Cacciari, Matteo; Salam, Gavin P.; Soyez, Gregory Journal of High Energy Physics, Vol. 2008, Issue 04 https://doi.org/10.1088/1126-6708/2008/04/063	journal	April 2008
Semi-supervised anomaly detection – towards model-independent searches of new physics Kuusela, Mikael; Vatanen, Tommi; Malmi, Eric Journal of Physics: Conference Series, Vol. 368 https://doi.org/10.1088/1742-6596/368/1/012032	journal	June 2012
‘Flux+Mutability’: a conditional generative approach to one-class classification and anomaly detection Fanelli, C.; Giroux, J.; Papandreou, Z. Machine Learning: Science and Technology, Vol. 3, Issue 4 https://doi.org/10.1088/2632-2153/ac9bcb	journal	November 2022
Exploring the space of jets with CMS open data Komiske, Patrick T.; Mastandrea, Radha; Metodiev, Eric M. Physical Review D, Vol. 101, Issue 3 https://doi.org/10.1103/PhysRevD.101.034009	journal	February 2020
Searching for new physics with deep autoencoders Farina, Marco; Nakai, Yuichiro; Shih, David Physical Review D, Vol. 101, Issue 7 https://doi.org/10.1103/PhysRevD.101.075021	journal	April 2020
Anomaly detection with density estimation Nachman, Benjamin; Shih, David Physical Review D, Vol. 101, Issue 7 https://doi.org/10.1103/PhysRevD.101.075042	journal	April 2020
Novelty detection meets collider physics Hajer, Jan; Li, Ying-Ying; Liu, Tao Physical Review D, Vol. 101, Issue 7 https://doi.org/10.1103/PhysRevD.101.076015	journal	April 2020
Online-compatible unsupervised nonresonant anomaly detection Mikuni, Vinicius; Nachman, Benjamin; Shih, David Physical Review D, Vol. 105, Issue 5 https://doi.org/10.1103/PhysRevD.105.055006	journal	March 2022
Which metric on the space of collider events? Cai, Tianji; Cheng, Junyi; Craig, Katy Physical Review D, Vol. 105, Issue 7 https://doi.org/10.1103/PhysRevD.105.076003	journal	April 2022
Anomaly detection in high-energy physics using a quantum autoencoder Ngairangbam, Vishal S.; Spannowsky, Michael; Takeuchi, Michihisa Physical Review D, Vol. 105, Issue 9 https://doi.org/10.1103/PhysRevD.105.095004	journal	May 2022
Creating simple, interpretable anomaly detectors for new physics in jet substructure Bradshaw, Layne; Chang, Spencer; Ostdiek, Bryan Physical Review D, Vol. 106, Issue 3 https://doi.org/10.1103/PhysRevD.106.035014	journal	August 2022
Self-supervised anomaly detection for new physics Dillon, Barry M.; Mastandrea, Radha; Nachman, Benjamin Physical Review D, Vol. 106, Issue 5 https://doi.org/10.1103/PhysRevD.106.056005	journal	September 2022
Extending the search for new resonances with machine learning Collins, Jack H.; Howe, Kiel; Nachman, Benjamin Physical Review D, Vol. 99, Issue 1 https://doi.org/10.1103/PhysRevD.99.014038	journal	January 2019
Learning new physics from a machine D’Agnolo, Raffaele Tito; Wulzer, Andrea Physical Review D, Vol. 99, Issue 1 https://doi.org/10.1103/PhysRevD.99.015014	journal	January 2019
Anomaly Detection for Resonant New Physics with Machine Learning Collins, Jack; Howe, Kiel; Nachman, Benjamin Physical Review Letters, Vol. 121, Issue 24 https://doi.org/10.1103/PhysRevLett.121.241803	journal	December 2018
Metric Space of Collider Events Komiske, Patrick T.; Metodiev, Eric M.; Thaler, Jesse Physical Review Letters, Vol. 123, Issue 4 https://doi.org/10.1103/PhysRevLett.123.041801	journal	July 2019
Divide and Conquer the Embedding Space for Metric Learning Sanakoyeu, Artsiom; Tschernezki, Vadim; Buchler, Uta 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2019.00056	conference	June 2019
FastJet user manual: (for version 3.0.2) Cacciari, Matteo; Salam, Gavin P.; Soyez, Gregory The European Physical Journal C, Vol. 72, Issue 3 https://doi.org/10.1140/epjc/s10052-012-1896-2	journal	March 2012
Tuning PYTHIA 8.1: the Monash 2013 tune Skands, P.; Carrazza, S.; Rojo, J. The European Physical Journal C, Vol. 74, Issue 8 https://doi.org/10.1140/epjc/s10052-014-3024-y	journal	August 2014
Finding new physics without learning about it: anomaly detection as a tool for searches at colliders Crispim Romão, M.; Castro, N. F.; Pedro, R. The European Physical Journal C, Vol. 81, Issue 1 https://doi.org/10.1140/epjc/s10052-020-08807-w	journal	January 2021
Use of a generalized energy Mover’s distance in the search for rare phenomena at colliders Crispim Romão, M.; Castro, N. F.; Milhano, J. G. The European Physical Journal C, Vol. 81, Issue 2 https://doi.org/10.1140/epjc/s10052-021-08891-6	journal	February 2021
Anomaly detection from mass unspecific jet tagging Aguilar-Saavedra, J. A. The European Physical Journal C, Vol. 82, Issue 2 https://doi.org/10.1140/epjc/s10052-022-10058-w	journal	February 2022
Deep Set Auto Encoders for Anomaly Detection in Particle Physics Ostdiek, Bryan SciPost Physics, Vol. 12, Issue 1 https://doi.org/10.21468/SciPostPhys.12.1.045	journal	January 2022
Rare and Different: Anomaly Scores from a combination of likelihood and out-of-distribution models to detect new physics at the LHC Caron, Sascha; Hendriks, Luc; Verheyen, Rob SciPost Physics, Vol. 12, Issue 2 https://doi.org/10.21468/SciPostPhys.12.2.077	journal	January 2022
QCD or what? Heimel, Theo; Kasieczka, Gregor; Plehn, Tilman SciPost Physics, Vol. 6, Issue 3 https://doi.org/10.21468/SciPostPhys.6.3.030	journal	January 2019
Glove: Global Vectors for Word Representation Pennington, Jeffrey; Socher, Richard; Manning, Christopher Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) https://doi.org/10.3115/v1/d14-1162	conference	January 2014
Event-Based Anomaly Detection for Searches for New Physics Chekanov, Sergei; Hopkins, Walter Universe, Vol. 8, Issue 10 https://doi.org/10.3390/universe8100494	journal	September 2022

Similar Records

Quasitoric manifolds and small covers over properly coloured polytopes: immersions and embeddings

Journal Article · Sat Apr 30 00:00:00 EDT 2016 · Sbornik. Mathematics · OSTI ID:22875621

Blow up of solutions to the nonlinear Schroedinger equations on manifolds

Journal Article · Tue May 15 00:00:00 EDT 2007 · Journal of Mathematical Physics · OSTI ID:20929727

A configuration manifold embedding model for dynamic control of redundant robots

Journal Article · Tue Feb 29 23:00:00 EST 2000 · International Journal of Robotics Research · OSTI ID:20015663

Related Subjects

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS
Dark matter at colliders
Jets and jet substructure
Physics

Neural embedding: learning the embedding of the manifold of physics data

Citation Formats

References (43)

Similar Records

Related Subjects