Flow Annealed Importance Sampling Bootstrap meets Differentiable Particle Physics

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kofler, Annalena, Stimper, Vincent, Mikhasenko, Mikhail, Kagan, Michael, Heinrich, Lukas
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915302535593984
author Kofler, Annalena
Stimper, Vincent
Mikhasenko, Mikhail
Kagan, Michael
Heinrich, Lukas
author_facet Kofler, Annalena
Stimper, Vincent
Mikhasenko, Mikhail
Kagan, Michael
Heinrich, Lukas
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16234
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Flow Annealed Importance Sampling Bootstrap meets Differentiable Particle Physics
Kofler, Annalena
Stimper, Vincent
Mikhasenko, Mikhail
Kagan, Michael
Heinrich, Lukas
High Energy Physics - Phenomenology
Machine Learning
Computational Physics
Data Analysis, Statistics and Probability
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.
title Flow Annealed Importance Sampling Bootstrap meets Differentiable Particle Physics
topic High Energy Physics - Phenomenology
Machine Learning
Computational Physics
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2411.16234