Geometric Priors for Scientific Generative Models in Inertial Confinement Fusion
Machine Learning
2021-11-29 v1 Computer Vision and Pattern Recognition
Abstract
In this paper, we develop a Wasserstein autoencoder (WAE) with a hyperspherical prior for multimodal data in the application of inertial confinement fusion. Unlike a typical hyperspherical generative model that requires computationally inefficient sampling from distributions like the von Mis Fisher, we sample from a normal distribution followed by a projection layer before the generator. Finally, to determine the validity of the generated samples, we exploit a known relationship between the modalities in the dataset as a scientific constraint, and study different properties of the proposed model.
Keywords
Cite
@article{arxiv.2111.12798,
title = {Geometric Priors for Scientific Generative Models in Inertial Confinement Fusion},
author = {Ankita Shukla and Rushil Anirudh and Eugene Kur and Jayaraman J. Thiagarajan and Peer-Timo Bremer and Brian K. Spears and Tammy Ma and Pavan Turaga},
journal= {arXiv preprint arXiv:2111.12798},
year = {2021}
}
Comments
5 pages, 4 figures, Fourth Workshop on Machine Learning and the Physical Sciences, NeurIPS 2021