CERN Accelerating science

Talk
Title	Adversarial Tuning of Perturbative Parameters in Non-Differentiable Physics Simulators
Video	If you experience any problem watching the video, click the download button below Download Embed Mp4: Medium (800 kbps) High (2000 kbps) More.. 800 kbps 800 kbps 1000 kbps Copy-paste this code into your page: <iframe width="640" height="360" frameborder="0" src="https://cds.cern.ch/video/2312417?showTitle=true" allowfullscreen></iframe> Copy-paste this code into your page to include both slides and lecture: <iframe src="https://mediastream.cern.ch/MediaArchive/Video/Public2/weblecture-player/index.html?year=2018&lecture=668017c26" width="1020px" height="600px" allowfullscreen scrolling="no" frameborder="0"></iframe>
Author(s)	Paganini, Michela (speaker) (Yale University (US))
Corporate author(s)	CERN. Geneva
Imprint	2018-04-10. - Streaming video.
Series	(Machine Learning) (2nd IML Machine Learning Workshop)
Lecture note	on 2018-04-10T11:00:00
Subject category	Machine Learning
Abstract	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 generator. This represents a step forward compared to unidimensional distributional template-matching methods.
Copyright/License	© 2018-2024 CERN
Submitted by	paul.seyfert@cern.ch