EP-IT Data Science Seminars

New Ideas for LHC Theory using Machine Learning

by Tilman Plehn

503/1-001 - Council Chamber (CERN)

503/1-001 - Council Chamber


Show room on map

Modern machine learning is having significant impact on essentially all aspects of LHC physics. The reason is that LHC physics uniquely combines vast and highly complex data sets with precise first-principles predictions. I will introduce a range of applications of machine learning to LHC theory and show how we can benefit from these new concepts and methods. Flow-based invertible networks can supplement and enhance precision simulations, including uncertainty estimates and a high level of control through a new, GAN-inspired architecture. Such networks can also unfold detector simulations or the QCD parton shower in a mathematically consistent manner, eventually providing event-wise likelihoods for the matrix element methods. Finally, I will discuss the exciting new avenue of using symbolic regression to learn optimal observables in Higgs physics.

Tilman Plehn is a theoretical physicists at Heidelberg University. His research focus is on searches for new physics at the LHC, including numerical aspects like global analyses and simulations. Together with his group he has been working on applications of modern machine learning to LHC physics since 2017.

Organized by

M. Girone, M. Elsing, L. Moneta, M. Pierini

EP/IT Data Science Seminar
Zoom Meeting ID
EP/IT Data Science seminar
Lorenzo Moneta
Alternative hosts
Maria Girone, Markus Elsing, EP Seminars and Colloquia, Maurizio Pierini, Caroline Cazenoves
Useful links
Join via phone
Zoom URL