Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis

By Luke de Oliveira, Michela Paganini, Benjamin Nachman. 2017

306 citations recorded by the source corpus.

We provide a bridge between generative modeling in the Machine Learning community and simulated physical processes in high energy particle physics by applying a novel Generative Adversarial Network (GAN) architecture to the production of jet images—2D representations of energy depositions from particles interacting with a calorimeter. We propose a simple architecture, the Location-Aware Generative Adversarial Network, that learns to produce realistic radiation patterns from simulated high energy particle collisions. The pixel intensities of GAN-generated images faithfully span over many orders of magnitude and exhibit the desired low-dimensional physical properties (i.e., jet mass, n-subjettiness, etc.). We shed light on limitations, and provide a novel empirical validation of image quality and validity of GAN-produced simulations of the natural world. This work provides a base for further explorations of GANs for use in faster simulation in high energy particle physics.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Statistical and Nonlinear Physics

In Generative Models

Citations in the corpus

Searching for new physics with deep autoencoders (2018, background): “Applications of deep learning in high energy physics do not stop at classification tasks: pile-up removal [32], generative models [33] and many others (for a review and more references, we refer to [34]) have all been studied.”
How Generative Adversarial Networks and Its Variants Work : An Overview of GAN (2017, methodology): “3 Other applications GAN variants such as CaloGAN [86] and LAGAN [21] are applied to physics, attempting to generate particle images to represent energy distributions.”
GANs for Biological Image Synthesis (2017, methodology): “Models with adversarial losses have been used in a wide range of applications, such as image generation [8, 38], domain adaptation [12], text-to-image synthesis [39], synthesis of 3D shapes [49] and texture [23], image-to-image translation [18], image super resolution [22] and even generating radiat”