The LHC Olympics Challenge: Machine learning ushers in a new paradigm for particle searches

January 26, 2021

In a recent article in the CERN EP Newsletter, BIDS Research Affiliate Ben Nachman describes an emerging paradigm for data-driven, model-agnostic new physics searches at colliders, and how it aims to leverage recent breakthroughs in anomaly detection and machine learning.

LHC Olympics 2020 - banner imageTo develop standard datasets and benchmark new anomaly detection methods within this framework, Nachman — along with BIDS Faculty Affiliate Uroš Seljak and a team of colleagues from around the world — participated in the LHC Olympics 2020, a community challenge accompanied by a set of simulated collider events. The team has recently released a paper that reviews the LHC Olympics 2020 challenge, including an overview of the competition, a description of the participants/teams and the methods they deployed in the competition, lessons learned from the experience, and implications for data analyses with future datasets as well as future colliders. Nachman was one of the challenge co-organizers, and led a team that recently applied methods to collider data, and Seljak was the PI of the winning team from the blind challenge. 

The Large Hadron Collider (LHC) is the world’s largest and most powerful particle accelerator. It was first started in September 2008, and remains the latest addition to CERN’s accelerator complex. The LHC consists of a 27-kilometre ring of superconducting magnets with a number of accelerating structures to boost the energy of the particles along the way. The beams inside the LHC are made to collide at four locations around the accelerator ring, corresponding to the positions of four particle detectors – ATLAS, CMS, ALICE and LHCb.

According to Nachman, "A data-driven revolution has started with machine learning as its catalyst. We are well-equipped to explore the complex LHC data in new ways with immense potential for discovery... This LHC Olympics has been a starting point for a new chapter in collider physics that will produce exciting physics results from the current datasets as well from the datasets of the future at the LHC and beyond."

The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics 
January 20, 2021  |

Machine learning ushers in a new paradigm for particle searches at the LHC 
December 10, 2020  |  Ben Nachman  |  CERN EP Newsletter

Berkeley Lab Cosmologists Are Top Contenders in Machine Learning Challenge 
March 20, 2020  |   Glenn Roberts, Jr.  |  Berkeley Lab News Center

Machine learning qualitatively changes the search for new particles 
May 13, 2020  |  ATLAS Collaboration

Featured Fellows

Benjamin Nachman

Physics Division, LBNL
Research Affiliate

Uroš Seljak

Physics, Astronomy, Berkeley Center for Cosmological Physics
Faculty Affiliate