Jul 6 – 8, 2021
Europe/Zurich timezone

Jet Metrics and Autoencoders

Jul 6, 2021, 3:20 PM


Rashmish Mishra (Harvard University)


The Energy Movers Distance was recently proposed as an advantageous metric to distinguish certain types of signals at the LHC. We explore generalizations of this distance to multiple families of signals and find similar performance anomaly detection through variational autoencoders. We investigate this connection by exploring the correlation of event distances with distances in the latent space of the autoencoder.

Affiliation Harvard University
Academic Rank Postdc

Primary authors

Katherine Fraser (Harvard University) Samuel Homiller (Harvard) Rashmish Mishra (Harvard University) Bryan Ostdiek (Harvard University) Matthew Schwartz

Presentation materials