GANplifying event samples
Anja Butter, Sascha Diefenbacher, Gregor Kasieczka, Benjamin Nachman, Tilman Plehn
Abstract
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.
Topics & Concepts
Event (particle physics)Generative grammarSample (material)Curse of dimensionalitySimple (philosophy)Computer scienceGenerative modelSample size determinationStatisticsArtificial intelligenceMachine learningMathematicsPhysicsQuantum mechanicsThermodynamicsEpistemologyPhilosophyComputational Physics and Python ApplicationsGaussian Processes and Bayesian InferenceParticle physics theoretical and experimental studies