Particle Cloud Generation with Message Passing GANS
Dec 6, 2021
Speakers
Raghav Kansal
Speaker · 0 followers
Javier Duarte
Speaker · 0 followers
Breno Orzari
Speaker · 0 followers
Thiago Tomei
Speaker · 0 followers
Maurizio Pierini
Speaker · 0 followers
Mary Touranakou
Speaker · 0 followers
Jean-Roch Vlimant
Speaker · 0 followers
Dimitrios Gunopulos
Speaker · 0 followers
About
In high energy physics (HEP), jets are collections of correlated particles produced ubiquitously in particle collisions such as those at the CERN Large Hadron Collider (LHC). Machine-learning-based generative models, such as generative adversarial networks (GANs), have the potential to significantly accelerate LHC jet simulations. However, despite jets having a natural representation as a set of particles in momentum-space, a.k.a. a particle cloud, to our knowledge there exist no generative models applied to such a dataset. We introduce a new particle cloud dataset (JetNet), and, due to similarities between particle and point clouds, apply to it existing point cloud GANs. Results are evaluated using (1) the 1-Wasserstein distance between high- and low-level feature distributions, (2) a newly developed Fréchet ParticleNet Distance, and (3) the coverage and (4) minimum matching distance metrics. Existing GANs are found to be inadequate for physics applications, hence we develop a new message passing GAN (MPGAN), which outperforms existing point cloud GANs on virtually every metric and shows promise for use in HEP. We propose JetNet as a novel point-cloud-style dataset for the machine learning community to experiment with, and set MPGAN as a benchmark to improve upon for future generative models.In high energy physics (HEP), jets are collections of correlated particles produced ubiquitously in particle collisions such as those at the CERN Large Hadron Collider (LHC). Machine-learning-based generative models, such as generative adversarial networks (GANs), have the potential to significantly accelerate LHC jet simulations. However, despite jets having a natural representation as a set of particles in momentum-space, a.k.a. a particle cloud, to our knowledge there exist no generative mode…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Contextual Bandits: Bridging Theory and Practice
Watch later
Susan Athey, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Fairness:: Individuality in Human-Centered AI
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Autonomous Debris Pile Estimation Challenge
Watch later
Bill Basener, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
High-dimensional hierarchical modeling with exchangeability of effects across covariates
Watch later
Brian Trippe, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning Contraction Policies from Offline Data
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift
Watch later
Kehang Han, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%