Profile Likelihoods on ML-Steroids

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Heimel, Theo, Plehn, Tilman, Schmal, Nikita
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913735497482240
author Heimel, Theo
Plehn, Tilman
Schmal, Nikita
author_facet Heimel, Theo
Plehn, Tilman
Schmal, Nikita
contents Profile likelihoods, for instance, describing global SMEFT analyses at the LHC are numerically expensive to construct and evaluate. Especially profiled likelihoods are notoriously unstable and noisy. We show how modern numerical tools, similar to neural importance sampling, lead to a huge numerical improvement and allow us to evaluate the complete SFitter SMEFT likelihood in five hours on a single GPU.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00942
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Profile Likelihoods on ML-Steroids
Heimel, Theo
Plehn, Tilman
Schmal, Nikita
High Energy Physics - Phenomenology
Profile likelihoods, for instance, describing global SMEFT analyses at the LHC are numerically expensive to construct and evaluate. Especially profiled likelihoods are notoriously unstable and noisy. We show how modern numerical tools, similar to neural importance sampling, lead to a huge numerical improvement and allow us to evaluate the complete SFitter SMEFT likelihood in five hours on a single GPU.
title Profile Likelihoods on ML-Steroids
topic High Energy Physics - Phenomenology
url https://arxiv.org/abs/2411.00942