GANplifying Event Samples

08/14/2020
by   Anja Butter, et al.
0

A critical question concerning generative networks applied to event generation in particle physics is if the generated events add statistical precision beyond the training sample. We show for a simple example with increasing dimensionality how generative networks indeed amplify the training statistics. We quantify their impact through an amplification factor or equivalent numbers of sampled events.

READ FULL TEXT
06/01/2021

A survey of machine learning-based physics event generation

Event generators in high-energy nuclear and particle physics play an imp...
10/11/2018

Energy Flow Networks: Deep Sets for Particle Jets

A key question for machine learning approaches in particle physics is ho...
01/20/2022

Statistical prediction of extreme events from small datasets

We propose Echo State Networks (ESNs) to predict the statistics of extre...
06/14/2021

Toward Diverse Precondition Generation

Language understanding must identify the logical connections between eve...
04/17/2020

Scaling the training of particle classification on simulated MicroBooNE events to multiple GPUs

Measurements in Liquid Argon Time Projection Chamber (LArTPC) neutrino d...
05/02/2019

Reliability of relational event model estimates under sampling: how to fit a relational event model to 360 million dyadic events

We assess the reliability of relational event model parameters estimated...
07/05/2022

A general framework to quantify the event importance in multi-event contests

We propose a statistical framework for quantifying the importance of sin...