The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
Abstract
A new paradigm for data-driven, model-agnostic new physics searches at colliders is emerging, and aims to leverage recent breakthroughs in anomaly detection and machine learning. In order to develop and benchmark new anomaly detection methods within this framework, it is essential to have standard datasets. To this end, we have created the LHC Olympics 2020, a community challenge accompanied by a set of simulated collider events. Participants in these Olympics have developed their methods using an R&D dataset and then tested them on black boxes: datasets with an unknown anomaly (or not). This paper will review the LHC Olympics 2020 challenge, including an overview of the competition, a description of methods deployed in the competition, lessons learned from the experience, and implications for data analyses with future datasets as well as future colliders.
Keywords
Cite
@article{arxiv.2101.08320,
title = {The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics},
author = {Gregor Kasieczka and Benjamin Nachman and David Shih and Oz Amram and Anders Andreassen and Kees Benkendorfer and Blaz Bortolato and Gustaaf Brooijmans and Florencia Canelli and Jack H. Collins and Biwei Dai and Felipe F. De Freitas and Barry M. Dillon and Ioan-Mihail Dinu and Zhongtian Dong and Julien Donini and Javier Duarte and D. A. Faroughy and Julia Gonski and Philip Harris and Alan Kahn and Jernej F. Kamenik and Charanjit K. Khosa and Patrick Komiske and Luc Le Pottier and Pablo Martín-Ramiro and Andrej Matevc and Eric Metodiev and Vinicius Mikuni and Inês Ochoa and Sang Eon Park and Maurizio Pierini and Dylan Rankin and Veronica Sanz and Nilai Sarda and Urous Seljak and Aleks Smolkovic and George Stein and Cristina Mantilla Suarez and Manuel Szewc and Jesse Thaler and Steven Tsan and Silviu-Marian Udrescu and Louis Vaslin and Jean-Roch Vlimant and Daniel Williams and Mikaeel Yunus},
journal= {arXiv preprint arXiv:2101.08320},
year = {2021}
}
Comments
108 pages, 53 figures, 3 tables