MACK: Mismodeling Addressed with Contrastive Knowledge

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sheldon, Liam Rankin, Rankin, Dylan Sheldon, Harris, Philip
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912361796861952
author Sheldon, Liam Rankin
Rankin, Dylan Sheldon
Harris, Philip
author_facet Sheldon, Liam Rankin
Rankin, Dylan Sheldon
Harris, Philip
contents The use of machine learning methods in high energy physics typically relies on large volumes of precise simulation for training. As machine learning models become more complex they can become increasingly sensitive to differences between this simulation and the real data collected by experiments. We present a generic methodology based on contrastive learning which is able to greatly mitigate this negative effect. Crucially, the method does not require prior knowledge of the specifics of the mismodeling. While we demonstrate the efficacy of this technique using the task of jet-tagging at the Large Hadron Collider, it is applicable to a wide array of different tasks both in and out of the field of high energy physics.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13947
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MACK: Mismodeling Addressed with Contrastive Knowledge
Sheldon, Liam Rankin
Rankin, Dylan Sheldon
Harris, Philip
High Energy Physics - Phenomenology
Machine Learning
High Energy Physics - Experiment
The use of machine learning methods in high energy physics typically relies on large volumes of precise simulation for training. As machine learning models become more complex they can become increasingly sensitive to differences between this simulation and the real data collected by experiments. We present a generic methodology based on contrastive learning which is able to greatly mitigate this negative effect. Crucially, the method does not require prior knowledge of the specifics of the mismodeling. While we demonstrate the efficacy of this technique using the task of jet-tagging at the Large Hadron Collider, it is applicable to a wide array of different tasks both in and out of the field of high energy physics.
title MACK: Mismodeling Addressed with Contrastive Knowledge
topic High Energy Physics - Phenomenology
Machine Learning
High Energy Physics - Experiment
url https://arxiv.org/abs/2410.13947