Applications of Lipschitz neural networks to the Run 3 LHCb trigger system

• DOI: 10.48550/arxiv.2312.14265
• Publication Date: 2023-01-01
• Authors: B. Delaney; N. Schulte; G. Ciezarek; N. S. Nolte; Mike Williams; J. Albrecht
• Keywords: Robustness

The operating conditions defining the current data taking campaign at Large Hadron Collider, known as Run 3, present unparalleled challenges for real-time acquisition workflow of LHCb experiment CERN. To address anticipated surge in luminosity and consequent event rate, is transitioning to a fully software-based trigger system. This evolution necessitated innovations hardware configurations, software paradigms, algorithmic design. A significant advancement integration monotonic Lipschitz neural networks into These deep learning models offer certified robustness against detector instabilities, ability encode domain-specific inductive biases. Such properties are crucial inclusive heavy-flavour triggers and, most notably, topological designed inclusively select $b$-hadron candidates by exploiting unique kinematic decay topologies beauty decays. paper describes recent progress integrating triggers, highlighting resulting enhanced sensitivity highly displaced multi-body produced within acceptance.