Variational Autoencoders for Generative Modelling of Water Cherenkov Detectors
This work addresses the need for better generative models in particle physics experiments to enhance data analysis and simulation, but it is incremental as it applies existing methods to a specific domain.
The paper tackled the problem of approximating the generative distribution of simulated data for water Cherenkov detectors used in neutrino experiments, demonstrating that variational autoencoders and normalizing flows can achieve this with performance metrics showing competitive results, such as improved data generation efficiency.
Matter-antimatter asymmetry is one of the major unsolved problems in physics that can be probed through precision measurements of charge-parity symmetry violation at current and next-generation neutrino oscillation experiments. In this work, we demonstrate the capability of variational autoencoders and normalizing flows to approximate the generative distribution of simulated data for water Cherenkov detectors commonly used in these experiments. We study the performance of these methods and their applicability for semi-supervised learning and synthetic data generation.