• Open Access

Creating simple, interpretable anomaly detectors for new physics in jet substructure

Layne Bradshaw, Spencer Chang, and Bryan Ostdiek
Phys. Rev. D 106, 035014 – Published 12 August 2022

Abstract

Anomaly detection with convolutional autoencoders is a popular method to search for new physics in a model-agnostic manner. These techniques are powerful, but they are still a “black box,” since we do not know what high-level physical observables determine how anomalous an event is. To address this, we adapt a recently proposed technique by Faucett et al. [Phys. Rev. D 103, 036020 (2021).], which maps out the physical observables learned by a neural network classifier, to the case of anomaly detection. We propose two different strategies that use a small number of high-level observables to mimic the decisions made by the autoencoder on background events, one designed to directly learn the output of the autoencoder, and the other designed to learn the difference between the autoencoder’s outputs on a pair of events. Despite the underlying differences in their approach, we find that both strategies have similar ordering performance as the autoencoder and independently use the same six high-level observables. From there, we compare the performance of these networks as anomaly detectors. We find that both strategies perform similarly to the autoencoder across a variety of signals, giving a nontrivial demonstration that learning to order background events transfers to ordering a variety of signal events.

  • Figure
  • Figure
  • Figure
  • Figure
  • Figure
  • Figure
  • Figure
1 More
  • Received 16 March 2022
  • Accepted 11 July 2022

DOI:https://doi.org/10.1103/PhysRevD.106.035014

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI. Funded by SCOAP3.

Published by the American Physical Society

Physics Subject Headings (PhySH)

Particles & Fields

Authors & Affiliations

Layne Bradshaw* and Spencer Chang

  • Department of Physics and Institute for Fundamental Science, University of Oregon, Eugene, Oregon 97403, USA

Bryan Ostdiek

  • Department of Physics, Harvard University, Cambridge, Massachusetts 02318, USA and The NSF AI Institute for Artificial Intelligence and Fundamental Interactions

  • *layneb@uoregon.edu
  • chang2@uoregon.edu

Article Text

Click to Expand

References

Click to Expand
Issue

Vol. 106, Iss. 3 — 1 August 2022

Reuse & Permissions
Author publication services for translation and copyediting assistance advertisement

Authorization Required


×
×

Images

×

Sign up to receive regular email alerts from Physical Review D

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

×

Log In

Cancel
×

Search


Article Lookup

Paste a citation or DOI

Enter a citation
×