Abstract
The CERN Large Hadron Collider (LHC) produces O(10,000) exabytes of raw data annually from high-energy proton collisions. Handling this volume under strict compute and storage limits requires real-time event filtering capable of processing millions of collisions per second. A multi-tier architecture of ASICs, FPGAs, CPUs, and GPUs reconstructs and analyzes events, rejecting >98% of data within microseconds.
With the transition to the High-Luminosity Large Hadron Collider (HL-LHC), the first trigger stage, located in radiation-shielded caverns ~100 m underground, must handle data rates approaching ~5% of global internet traffic and significantly increased event complexity. Maintaining physics sensitivity therefore requires highly efficient machine-learning algorithms optimized for real-time inference with extreme throughput and ultra-low latency.
In this talk, we will discuss emerging techniques for low-power, low-latency inference, including hardware-aware model design, quantization, sparsity, and hardware-software co-design. Using examples from particle physics and other domains, we will show how real-time machine learning is both a practical necessity and a powerful tool for scientific discovery.
Speaker
Thea Klaeboe Aarrestad
Particle Physics and Real-Time ML @CERN @ETH Zürich
Thea Klæboe Aarrestad is a particle physicist and fellow at the Institute for Particle Physics and Astrophysics at ETH Zürich. She earned a PhD in particle physics from the University of Zurich and previously worked as a research fellow at CERN in Geneva. Her work centers on applying machine learning to particle physics, with an emphasis on real-time techniques for discovering new phenomena, including low-power nanosecond inference on FPGAs and ML-based anomaly detection for analyzing proton collision data from the Large Hadron Collider. She was awarded the Young Experimental Physicist Prize by the European Physical Society for her contributions to integrating machine learning into experimental particle physics.
Find Thea Klaeboe Aarrestad at:
Date
Wednesday Mar 18 / 10:35AM GMT ( 50 minutes )
Location
Mountbatten (6th Fl.)
