Oct 19 – 23, 2020
Europe/Zurich timezone

Invertible Networks or Partons to Detector and Back Again

Oct 21, 2020, 2:40 PM
20m
Regular talk 1 ML for data reduction : Application of Machine Learning to data reduction, reconstruction, building/tagging of intermediate object Workshop

Speaker

Anja Butter

Description

For simulations where the forward and the inverse directions have a physics meaning, invertible neural networks are especially useful. A conditional INN can invert a detector simulation in terms of high-level observables, specifically for ZW production at the LHC. It allows for a per-event statistical interpretation. Next, we allow for a variable number of QCD jets. We unfold detector effects and QCD radiation to a pre-defined hard process, again with a per-event probabilistic interpretation over parton-level phase space.

Primary authors

Presentation materials