Aug 21 – 25, 2017
University of Washington, Seattle
US/Pacific timezone

BDTs in the Level 1 Muon Endcap Trigger at CMS

Aug 21, 2017, 2:40 PM
107 (Alder Hall)


Alder Hall

Oral Track 2: Data Analysis - Algorithms and Tools Track 2: Data Analysis - Algorithms and Tools


Andrew Mathew Carnes (University of Florida (US))


The first implementation of Machine Learning inside a Level 1 trigger system at the LHC is presented. The Endcap Muon Track Finder at CMS uses Boosted Decision Trees to infer the momentum of muons based on 25 variables. All combinations of variables represented by 2^30 distinct patterns are evaluated using regression BDTs, whose output is stored in 2 GB look-up tables. These BDTs take advantage of complex correlations between variables, the inhomogeneous magnetic field, and non-linear effects to distinguish high momentum signal muons from the overwhelming low-momentum background. The new algorithm reduced the background rate by a factor of two compared to the previous analytic algorithm, with further improvements foreseen.

Primary authors

Andrew Mathew Carnes (University of Florida (US)) Andrew Brinkerhoff (University of Florida (US)) Darin Acosta (University of Florida (US)) Ivan Kresimir Furic (University of Florida (US)) Bobby Scurlock (University of Florida) Khristian Kotov (University of Florida (US)) Wei Shi (Rice University (US)) Alexander Madorsky (University of Florida (US))

Presentation materials

Peer reviewing