Cargando…
Adversarial Tuning of Perturbative Parameters in Non-Differentiable Physics Simulators
<!--HTML-->In this contribution, we present a method for tuning perturbative parameters in Monte Carlo simulation using a classifier loss in high dimensions. We use an LSTM trained on the radiation pattern inside jets to learn the parameters of the final state shower in the Pythia Monte Carlo...
Autor principal: | Paganini, Michela |
---|---|
Lenguaje: | eng |
Publicado: |
2018
|
Materias: | |
Acceso en línea: | http://cds.cern.ch/record/2312417 |
Ejemplares similares
-
Application of Generative Adversarial Networks (GANs) to jet images
por: Paganini, Michela
Publicado: (2017) -
Decorrelated Jet Substructure Tagging using Adversarial Neural Networks
por: Shimmin, Chase Owen
Publicado: (2017) -
Seminar: Open challenges for improving Generative Adversarial Networks (GANs)
por: Goodfellow, Ian
Publicado: (2017) -
Lund jet images from generative and cycle-consistent adversarial networks
por: Dreyer, Frederic Alexandre
Publicado: (2019) -
Fast calorimeter simulation in LHCb
por: Zakharov, Egor
Publicado: (2018)