Litcius/Paper detail

Search for New Phenomena in Two-Body Invariant Mass Distributions Using Unsupervised Machine Learning for Anomaly Detection at <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline"><mml:mrow><mml:msqrt><mml:mrow><mml:mi>s</mml:mi></mml:mrow></mml:msqrt><mml:mo>=</mml:mo><mml:mn>13</mml:mn><mml:mtext> </mml:mtext><mml:mtext> </mml:mtext><mml:mi>TeV</mml:mi></mml:mrow></mml:math> with the ATLAS Detector

G. Aad, B. Abbott, K. Abeling, Nils Julius Abicht, S. H. Abidi, A. Aboulhorma, H. Abramowicz, H. Abreu, Y. Abulaiti, A. C. Abusleme Hoffman, B. S. Acharya, C. Adam Bourdarios, L. Adamczyk, L. Adámek, S. V. Addepalli, M. J. Addison, J. Adelman, A. Adıgüzel, T. Adye, A. A. Affolder, Y. Afik, M. N. Agaras, J. Agarwala, A. Aggarwal, C. Agheorghiesei, A. Ahmad, F. Ahmadov, W. S. Ahmed, S. Ahuja, X. Ai, G. Aielli, A. Aikot, M. Ait Tamlihat, B. Aitbenchikh, I. Aizenberg, M. Akbiyik, T. P. A. Åkesson, A. V. Akimov, D. Akiyama, Nilima Nilesh Akolkar, K. Al Khoury, G. L. Alberghi, J. Albert, P. Albicocco, Guillaume Lucas Albouy, S. Alderweireldt, M. Aleksa, I. N. Aleksandrov, C. Alexa, T. Alexopoulos, F. Alfonsi, M. Algren, M. Alhroob, B. Ali, H. M. J. Ali, S. Ali, Samuel William Alibocus, M. Aliev, G. Alimonti, W. Alkakhi, C. Allaire, B. M. M. Allbrooke, Julia Frances Allen, C. Flores, P. P. Allport, A. Aloisio, F. Alonso, C. Alpigiani, M. Alvarez Estevez, A. Álvarez Fernández, Mario Alves Cardoso, M. G. Alviggi, M. Aly, Y. Amaral Coutinho, A. Ambler, C. Amelung, M. Amerl, C. G. Ames, D. Amidei, S. P. Amor Dos Santos, K. R. Amos, V. Ananiev, C. Anastopoulos, T. Andeen, J. K. Anders, S. Y. Andrean, A. Andreazza, S. Angelidakis, A. Angerami, A. V. Anisenkov, A. Annovi, C. Antel, M. T. Anthony, E. Antipov, M. Antonelli, F. Anulli, M. Aoki, T. Aoki, J. A. Aparisi Pozo, M. A. Aparo

2024Physical Review Letters29 citationsDOIOpen Access PDF

Abstract

Searches for new resonances are performed using an unsupervised anomaly-detection technique. Events with at least one electron or muon are selected from 140 fb^{-1} of pp collisions at sqrt[s]=13 TeV recorded by ATLAS at the Large Hadron Collider. The approach involves training an autoencoder on data, and subsequently defining anomalous regions based on the reconstruction loss of the decoder. Studies focus on nine invariant mass spectra that contain pairs of objects consisting of one light jet or b jet and either one lepton (e,μ), photon, or second light jet or b jet in the anomalous regions. No significant deviations from the background hypotheses are observed. Limits on contributions from generic Gaussian signals with various widths of the resonance mass are obtained for nine invariant masses in the anomalous regions.

Topics & Concepts

Anomaly detectionInvariant (physics)Artificial intelligenceComputer sciencePhysicsComputer graphics (images)Mathematical physicsParticle physics theoretical and experimental studiesParticle Detector Development and PerformanceComputational Physics and Python Applications