Hashing and metric learning for charged particle tracking
This addresses the computational bottleneck in particle physics for high-luminosity colliders like the HL-LHC, offering an incremental improvement over existing tracking methods.
The paper tackles the problem of charged particle tracking at high intensity particle colliders, where current combinatorial methods are inadequate due to hundreds of thousands of measurements per collision. It proposes a novel approach using hashing and metric learning, demonstrating significant speed improvement with a bucket tracking efficiency of 96% and a fake rate of 8% on simulated collisions.
We propose a novel approach to charged particle tracking at high intensity particle colliders based on Approximate Nearest Neighbors search. With hundreds of thousands of measurements per collision to be reconstructed e.g. at the High Luminosity Large Hadron Collider, the currently employed combinatorial track finding approaches become inadequate. Here, we use hashing techniques to separate measurements into buckets of 20-50 hits and increase their purity using metric learning. Two different approaches are studied to further resolve tracks inside buckets: Local Fisher Discriminant Analysis and Neural Networks for triplet similarity learning. We demonstrate the proposed approach on simulated collisions and show significant speed improvement with bucket tracking efficiency of 96% and a fake rate of 8% on unseen particle events.