View in EDS HTML Full Text PDF Full Text

Lorentz group equivariant autoencoders.

Saved in:
Bibliographic Details
Title: Lorentz group equivariant autoencoders.
Authors: Hao, Zichun1 (AUTHOR), Kansal, Raghav1,2 (AUTHOR) rkansal@ucsd.edu, Duarte, Javier1 (AUTHOR), Chernyavskaya, Nadezda3 (AUTHOR)
Source: European Physical Journal C -- Particles & Fields. Jun2023, Vol. 83 Issue 6, p1-15. 15p.
Subjects: Lorentz groups, Convolutional neural networks, Natural language processing, Machine learning, Particle physics, Computer vision, Deep learning
Abstract: There has been significant work recently in developing machine learning (ML) models in high energy physics (HEP) for tasks such as classification, simulation, and anomaly detection. Often these models are adapted from those designed for datasets in computer vision or natural language processing, which lack inductive biases suited to HEP data, such as equivariance to its inherent symmetries. Such biases have been shown to make models more performant and interpretable, and reduce the amount of training data needed. To that end, we develop the Lorentz group autoencoder (LGAE), an autoencoder model equivariant with respect to the proper, orthochronous Lorentz group SO + (3 , 1) , with a latent space living in the representations of the group. We present our architecture and several experimental results on jets at the LHC and find it outperforms graph and convolutional neural network baseline models on several compression, reconstruction, and anomaly detection metrics. We also demonstrate the advantage of such an equivariant model in analyzing the latent space of the autoencoder, which can improve the explainability of potential anomalies discovered by such ML models. [ABSTRACT FROM AUTHOR]
Copyright of European Physical Journal C -- Particles & Fields is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 164952689
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Lorentz group equivariant autoencoders.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Hao%2C+Zichun%22">Hao, Zichun</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Kansal%2C+Raghav%22">Kansal, Raghav</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> rkansal@ucsd.edu</i><br /><searchLink fieldCode="AR" term="%22Duarte%2C+Javier%22">Duarte, Javier</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Chernyavskaya%2C+Nadezda%22">Chernyavskaya, Nadezda</searchLink><relatesTo>3</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22European+Physical+Journal+C+--+Particles+%26+Fields%22">European Physical Journal C -- Particles & Fields</searchLink>. Jun2023, Vol. 83 Issue 6, p1-15. 15p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Lorentz+groups%22">Lorentz groups</searchLink><br /><searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Natural+language+processing%22">Natural language processing</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Particle+physics%22">Particle physics</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+vision%22">Computer vision</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: There has been significant work recently in developing machine learning (ML) models in high energy physics (HEP) for tasks such as classification, simulation, and anomaly detection. Often these models are adapted from those designed for datasets in computer vision or natural language processing, which lack inductive biases suited to HEP data, such as equivariance to its inherent symmetries. Such biases have been shown to make models more performant and interpretable, and reduce the amount of training data needed. To that end, we develop the Lorentz group autoencoder (LGAE), an autoencoder model equivariant with respect to the proper, orthochronous Lorentz group SO + (3 , 1) , with a latent space living in the representations of the group. We present our architecture and several experimental results on jets at the LHC and find it outperforms graph and convolutional neural network baseline models on several compression, reconstruction, and anomaly detection metrics. We also demonstrate the advantage of such an equivariant model in analyzing the latent space of the autoencoder, which can improve the explainability of potential anomalies discovered by such ML models. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of European Physical Journal C -- Particles & Fields is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=164952689
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1140/epjc/s10052-023-11633-5
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 15
        StartPage: 1
    Subjects:
      – SubjectFull: Lorentz groups
        Type: general
      – SubjectFull: Convolutional neural networks
        Type: general
      – SubjectFull: Natural language processing
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Particle physics
        Type: general
      – SubjectFull: Computer vision
        Type: general
      – SubjectFull: Deep learning
        Type: general
    Titles:
      – TitleFull: Lorentz group equivariant autoencoders.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Hao, Zichun
      – PersonEntity:
          Name:
            NameFull: Kansal, Raghav
      – PersonEntity:
          Name:
            NameFull: Duarte, Javier
      – PersonEntity:
          Name:
            NameFull: Chernyavskaya, Nadezda
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2023
              Type: published
              Y: 2023
          Identifiers:
            – Type: issn-print
              Value: 14346044
          Numbering:
            – Type: volume
              Value: 83
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: European Physical Journal C -- Particles & Fields
              Type: main
ResultId 1