Speaker
Mary Touranakou
(National and Kapodistrian University of Athens (GR))
Description
We study how to use Deep Variational Autoencoders for a fast simulation of jets of particles at the LHC. We represent jets as a list of constituents, characterized by their momenta. Starting from a simulation of the jet before detector effects, we train a Deep Variational Autoencoder to return the corresponding list of constituents after detection. Doing so, we bypass both the detector simulation, and the event reconstruction steps of a traditional event processing, potentially speeding up significantly the events generation workflow. Using as benchmark a convolutional VAE, we discuss how to customize the loss to improve accuracy.
Details
Mary Touranakou, PhD Student, National and Kapodistrian University of Athens, Greece, https://www.di.uoa.gr/
| Is this abstract from experiment? | Yes |
|---|---|
| Name of experiment and experimental site | CMS |
| Is the speaker for that presentation defined? | Yes |
| Internet talk | Maybe |
Primary authors
Mary Touranakou
(National and Kapodistrian University of Athens (GR))
Maurizio Pierini
(CERN)
Prof.
Dimitrios Gunopulos
(National and Kapodistrian University of Athens)
Javier Mauricio Duarte
(Univ. of California San Diego (US))
Raghav Kansal
(Univ. of California San Diego (US))
Jean-Roch Vlimant
(California Institute of Technology (US))
Breno Orzari
(UNESP - Universidade Estadual Paulista (BR))
Thiago Tomei Fernandez
(UNESP - Universidade Estadual Paulista (BR))
