How to Understand Limitations of Generative Networks

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Das, Ranit, Favaro, Luigi, Heimel, Theo, Krause, Claudius, Plehn, Tilman, Shih, David
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916109528072192
author Das, Ranit
Favaro, Luigi
Heimel, Theo
Krause, Claudius
Plehn, Tilman
Shih, David
author_facet Das, Ranit
Favaro, Luigi
Heimel, Theo
Krause, Claudius
Plehn, Tilman
Shih, David
contents Well-trained classifiers and their complete weight distributions provide us with a well-motivated and practicable method to test generative networks in particle physics. We illustrate their benefits for distribution-shifted jets, calorimeter showers, and reconstruction-level events. In all cases, the classifier weights make for a powerful test of the generative network, identify potential problems in the density estimation, relate them to the underlying physics, and tie in with a comprehensive precision and uncertainty treatment for generative networks.
format Preprint
id arxiv_https___arxiv_org_abs_2305_16774
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle How to Understand Limitations of Generative Networks
Das, Ranit
Favaro, Luigi
Heimel, Theo
Krause, Claudius
Plehn, Tilman
Shih, David
High Energy Physics - Phenomenology
Well-trained classifiers and their complete weight distributions provide us with a well-motivated and practicable method to test generative networks in particle physics. We illustrate their benefits for distribution-shifted jets, calorimeter showers, and reconstruction-level events. In all cases, the classifier weights make for a powerful test of the generative network, identify potential problems in the density estimation, relate them to the underlying physics, and tie in with a comprehensive precision and uncertainty treatment for generative networks.
title How to Understand Limitations of Generative Networks
topic High Energy Physics - Phenomenology
url https://arxiv.org/abs/2305.16774