Theory Seminar

Hunting new physics using Machine Learning techniques

by Charanjit Kaur

Monday, 6 May 2019 from to (Europe/Berlin)
at MPI Meeting rooms
Machine learning (ML) techniques are emerging as a competitive tool to look for new phenomena, as one can explore 
correlations in the multi-dimensional parameter space and in the complex experimental environment. Over the last couple 
of years, the High Energy Physics community has started adapting these techniques for various tasks, starting from the very 
first step of data collection i.e. trigger, event reconstruction, particle identification, heavy flavour  tagging, jet tagging  and signal 
and background classification. In this talk, I will give a brief introduction to the most commonly used ML techniques in HEP analyses. 
Then I will focus on my own work in the contest of SMEFT, where we exploit the kinematic information in the Higgs boson associated 
production with a massive vector boson (VH channel).  I will explain how these methods provide better sensitivities on the new physics 
deformations from the Standard Model. In the last part of my talk, I will discuss recent advances on new physics analyses based on ML techniques.