Flow Annealed Importance Sampling Bootstrap meets Differentiable Particle Physics
High Energy Physics - Phenomenology
2025-05-27 v2 Machine Learning
Computational Physics
Data Analysis, Statistics and Probability
Abstract
High-energy physics requires the generation of large numbers of simulated data samples from complex but analytically tractable distributions called matrix elements. Surrogate models, such as normalizing flows, are gaining popularity for this task due to their computational efficiency. We adopt an approach based on Flow Annealed importance sampling Bootstrap (FAB) that evaluates the differentiable target density during training and helps avoid the costly generation of training data in advance. We show that FAB reaches higher sampling efficiency with fewer target evaluations in high dimensions in comparison to other methods.
Cite
@article{arxiv.2411.16234,
title = {Flow Annealed Importance Sampling Bootstrap meets Differentiable Particle Physics},
author = {Annalena Kofler and Vincent Stimper and Mikhail Mikhasenko and Michael Kagan and Lukas Heinrich},
journal= {arXiv preprint arXiv:2411.16234},
year = {2025}
}
Comments
Accepted at "Machine Learning: Science and Technology"