Help us make Indico better by taking this survey! Aidez-nous à améliorer Indico en répondant à ce sondage !

Collider Cross Talk

Machine Learning based Anomaly Detection in High-Energy Particle Physics [TH, CMS]

by Michael Kraemer (Particle Physics), Thea Aarrestad (ETH Zurich (CH))

Europe/Zurich
4/2-011 - TH common room (CERN)

4/2-011 - TH common room

CERN

15
Show room on map
Description
Abstract:

In recent years, there has been an explosion of applications of machine learning-based anomaly detection for New Physics searches, enabling the identification of out-of-distribution events that may signal new phenomena or deviations from the Standard Model in a signal-agnostic way. Leveraging recent advances in machine learning, this approach has proven effective for monitoring complex detector systems and discovering rare or unexpected occurrences in large-scale collider datasets.
 
In this blackboard cross-talk, Thea Klaeboe Arrestad, an experimental physicist, and Michael Krämer, a theoretical physicist, will describe the principles of anomaly detection and its application in high-energy physics. They will discuss the challenges posed by porting these algorithms to the the vast and complex data from the Large Hadron Collider and learn how machine learning techniques have been successfully applied to search for anomalies in real experimental data. 
 
About the speakers:

Michael Krämer is a theoretical particle physicist at RWTH Aachen University, focusing on physics beyond the Standard Model and machine learning applications in fundamental physics. After completing his undergraduate studies at the University of Mainz, Michael held postdoctoral positions at DESY, the Rutherford Appleton Lab and CERN. Before moving to Aachen, he was a faculty member at the University of Edinburgh. 
 
Thea Klaeboe Aarrestad is a fellow at the Institute for Particle Physics and Astrophysics at ETH Zürich. She holds a PhD in particle physics from the University of Zürich and has worked as a research fellow at CERN in Geneva before moving to ETH. Her research centers on how Machine Learning can be applied to particle physics problems, especially focusing on using real-time Machine Learning (ML) and anomaly detection for discovering new physics phenomena. She has worked on tools for performing low-power, nanosecond ML inference on field-programmable gate arrays (FPGAs), as well as developing new methods for collecting and analysing proton collision data at the CERN Large Hadron Collider.