Speaker
Description
High-energy physics experiments face extreme data rates, requiring real-time trigger systems to reduce event throughput while preserving sensitivity to rare processes. Trigger systems have traditionally been constructed as modular chains of sequentially optimised algorithms, each optimised for a specific local objective with no guarantee of overall optimality.
We instead formulate trigger design as a constrained end-to-end optimisation problem. We implement a differentiable digital twin of an LHC jet trigger and optimise against a unified physics objective. The framework jointly optimises performance while incorporating physics and deployment constraints.
Using Higgs boson pair production as a benchmark, we observe an improvement in signal recall at a fixed false-positive rate, while preserving interpretable intermediate physics objects and monotonic calibration constraints. These results highlight end-to-end differential optimisation as a practical paradigm for next-generation real-time event selection systems.
| Do you plan to submit a 4-page extended abstract on OpenReview (only for Presentations/Posters)? | Maybe |
|---|