Machine Learning for Track Reconstruction at the LHC

The planned upgrade of the LHC to its high luminosity version (HL-LHC) around 2027 will bring about a drastic increase in instantaneous luminosity and simultaneous interactions per bunch crossing. Currently, most LHC experiments use Kalman Filter-based track reconstruction algorithms which exhibit outstanding physics performance but scale poorly with the amount of data produced in each bunch crossing. Therefore, the high energy physics community is currently performing intensive R\&D to commission new and/or improved algorithms for this crucial data reconstruction task. During this seminar, I will present many different approaches ranging from running existing algorithms on accelerated hardware to complete end-to-end neural network track reconstruction pipelines. A new algorithmic testbed for research in track reconstruction, ACTS, will also be discussed.