Next Generation Generative Neural Networks for HEP

Abstract

Initial studies have suggested generative adversarial networks (GANs) have promise as fast simulations within HEP. These studies, while promising, have been insufficiently precise and also, like GANs in general, suffer from stability issues. We apply GANs to to generate full particle physics events (not individual physics objects), explore conditioning of generated events based on physics theory parameters and evaluate the precision and generalization of the produced datasets. We apply this to SUSY mass parameter interpolation and pileup generation. We also discuss recent developments in convergence and representations that match the structure of the detector better than images. In addition we describe on-going work making use of large-scale distributed resources on the Cori supercomputer at NERSC, and developments to control distributed training via interactive jupyter notebook sessions. This will allow tackling high-resolution detector data; model selection and hyper-parameter tuning in a productive yet scalable deep learning environment. *

Non-Parametric Data-Driven Background Modelling using Conditional Probabilities

“…[20] and [21], respectively. Recent publications have also explored the idea of replacing the entire reconstructed-event generation pipeline with a GAN [17,[22][23][24][25][26][27]. Each of these applications differ in the nature of the training data used, but mostly use simulated training datasets.…”

Uncertainties associated with GAN-generated datasets in high energy physics

“…-Similarly, GANs could potentially be used to replace the underlying hard-scattering simulation, unless the reason for needing more events is to pickup subtle higher-order effects or improve the resolution of an underlying theory parameter (at the parton level), as is often the case. -Another example in the literature is the usage of GANs for pileup description [25,26], where a GAN is to be trained to generate minimumbias events. This could be appropriate in situations when simply resampling 2 from an existing library of minimum-bias events (used as GAN training data) is sufficient for the purposes of the analysis.…”

“…For example, the usage of GANs to only perform detector/calorimeter simulation was explored in [8][9][10][11][12][13][14][15][16][17][18][19][20][21]. The use of GANs for simulating the underlying hard process was considered in [22][23][24], while the use of GANs for pileup description was explored in [25,26]. Recent works have also explored the idea of replacing the entire reconstructed-event generation pipeline with a GAN [21,22,25,[27][28][29][30].…”

“…The use of GANs for simulating the underlying hard process was considered in [22][23][24], while the use of GANs for pileup description was explored in [25,26]. Recent works have also explored the idea of replacing the entire reconstructed-event generation pipeline with a GAN [21,22,25,[27][28][29][30]. Each of these applications of GANs would differ in the nature of the training data used.…”

Combine and conquer: event reconstruction with Bayesian Ensemble Neural Networks

“…For a review of these methodologies and more see refs [14,31],. and other examples[32][33][34][35][36][37][38][39][40][41][42][43][44] 2. Here the word "fitting" is used to simplify the text.…”