Open AccessComputation of Discrete Flows Over Networks via Constrained Wasserstein Barycenters
Author(s) -
Breno Orzari,
T. R. Fernandez Perez Tomei,
M. Pierini,
Mary Touranakou,
J. Duarte,
Raghav Kansal,
Jean Vlimant,
Dimitrios Gunopulos
Publication year - 2021
Language(s) - English
Resource type - Conference proceedings
DOI - 10.52591/lxai202107246
Subject(s) - discretization , computation , computer science , topology (electrical circuits) , network topology , exploit , set (abstract data type) , mathematical optimization , distribution (mathematics) , iterative method , theoretical computer science , mathematics , algorithm , computer network , mathematical analysis , computer security , combinatorics , programming language
We develop a generative neural network for the generation of sparse data in particle physics using a permutation-invariant and physics-informed loss function. The input dataset used in this study consists of the particle constituents of hadronic jets due to its sparsity and the possibility of evaluating the network’s ability to accurately describe the particles and jets properties. A variational autoencoder composed of convolutional layers in the encoder and decoder is used as the generator. The loss function consists of a reconstruction error term and the Kullback-Leibler divergence between the output of the encoder and the latent vector variables. The permutation-invariant loss on the particles’ properties is combined with two mean-squared error terms that measure the difference between input and output jets mass and transverse momentum, which improves the network’s generation capability as it imposes physics constraints, allowing the model to learn the kinematics of the jets.