Towards an Interpretable Data-driven Trigger System for High-throughput Physics Facilities
This addresses the challenge of real-time data processing for particle physics experiments, where bandwidths exceed 100 Tb/s, by providing an interpretable and efficient filtering solution, though it appears incremental as it builds on existing trigger systems.
The paper tackles the problem of designing a data-driven trigger system for high-throughput physics facilities like the LHC, aiming to filter data with minimal run-time cost while preserving or improving output distributions compared to hand-designed systems, resulting in a cost-effective model that maintains physics coverage.
Data-intensive science is increasingly reliant on real-time processing capabilities and machine learning workflows, in order to filter and analyze the extreme volumes of data being collected. This is especially true at the energy and intensity frontiers of particle physics where bandwidths of raw data can exceed 100 Tb/s of heterogeneous, high-dimensional data sourced from hundreds of millions of individual sensors. In this paper, we introduce a new data-driven approach for designing and optimizing high-throughput data filtering and trigger systems such as those in use at physics facilities like the Large Hadron Collider (LHC). Concretely, our goal is to design a data-driven filtering system with a minimal run-time cost for determining which data event to keep, while preserving (and potentially improving upon) the distribution of the output as generated by the hand-designed trigger system. We introduce key insights from interpretable predictive modeling and cost-sensitive learning in order to account for non-local inefficiencies in the current paradigm and construct a cost-effective data filtering and trigger model that does not compromise physics coverage.