26-30 July 2021
Europe/Berlin timezone

The Dark Machines Anomaly Score Initiative: Benchmark Data and Model Independent Classification for the Large Hadron Collider

28 Jul 2021, 17:15


Parallel session talk Searches for New Physics T10: Searches for New Physics


Joe Davies (Queen Mary University of London)


We describe the outcome of a data challenge to detect signals of new physics at the LHC using unsupervised machine learning algorithms conducted as part of the Dark Machines Initiative and the Les Houches 2019 workshop on Physics at TeV colliders. We first define and describe a large benchmark dataset, consisting of $>1$ Billion simulated LHC events corresponding to 10 fb$^{-1}$ of proton-proton collisions at a center-of-mass energy of 13 TeV. We then review a wide range of anomaly detection and density estimation algorithms, developed in the context of the data challenge, and we measure their performance in a set of realistic analysis environments. We draw a number of useful conclusions that will aid the development of unsupervised new physics searches during the third run of the LHC, and provide our benchmark dataset for future studies.

Collaboration / Activity Dark Machines Initiative

Primary authors

M van Beekveld (Oxford) Marcella Bona (Queen Mary University of London (UK)) Sascha Caron (Radboud University Nijmegen) A De Simone (SISSA) Joe Davies (Queen Mary University of London) Caterina Doglioni (Lund University) A Fabrin (University of Texas Arlington) Luc Hendriks J Howarth (University of Glasgow) Adil Jueid (Konkuk University, Seoul, Republic of Korea) A Leinweber (University of Adelaide) J Mamuzic (Instituto de F\'isica Corpuscular) E Merenyi (Rice University) A Morandini (RWTH Aachen University) Clara Nellist (Radboud University Nijmegen and NIKHEF (NL)) Bryan Ostdiek (Harvard University) M Pierini (CERN) B Ravina (University of Glasgow) Roberto Ruiz de Austri (Instituto de Fisica Corpuscular, IFIC-UV/CSIC, Valencia) Sezen Sekmen (Kyungpook National University (KR)) Dr Rob Verheyen (University College London) R Vilalta (University of Houston) M White (University of Adelaide) Z Zhang (Nikhef)

Presentation Materials