Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gandrakota, Abhijith, Zhang, Lily, Puli, Aahlad, Cranmer, Kyle, Ngadiuba, Jennifer, Ranganath, Rajesh, Tran, Nhan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909075599523840
author Gandrakota, Abhijith
Zhang, Lily
Puli, Aahlad
Cranmer, Kyle
Ngadiuba, Jennifer
Ranganath, Rajesh
Tran, Nhan
author_facet Gandrakota, Abhijith
Zhang, Lily
Puli, Aahlad
Cranmer, Kyle
Ngadiuba, Jennifer
Ranganath, Rajesh
Tran, Nhan
contents Anomaly, or out-of-distribution, detection is a promising tool for aiding discoveries of new particles or processes in particle physics. In this work, we identify and address two overlooked opportunities to improve anomaly detection for high-energy physics. First, rather than train a generative model on the single most dominant background process, we build detection algorithms using representation learning from multiple background types, thus taking advantage of more information to improve estimation of what is relevant for detection. Second, we generalize decorrelation to the multi-background setting, thus directly enforcing a more complete definition of robustness for anomaly detection. We demonstrate the benefit of the proposed robust multi-background anomaly detection algorithms on a high-dimensional dataset of particle decays at the Large Hadron Collider.
format Preprint
id arxiv_https___arxiv_org_abs_2401_08777
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning
Gandrakota, Abhijith
Zhang, Lily
Puli, Aahlad
Cranmer, Kyle
Ngadiuba, Jennifer
Ranganath, Rajesh
Tran, Nhan
High Energy Physics - Experiment
Machine Learning
High Energy Physics - Phenomenology
Data Analysis, Statistics and Probability
Anomaly, or out-of-distribution, detection is a promising tool for aiding discoveries of new particles or processes in particle physics. In this work, we identify and address two overlooked opportunities to improve anomaly detection for high-energy physics. First, rather than train a generative model on the single most dominant background process, we build detection algorithms using representation learning from multiple background types, thus taking advantage of more information to improve estimation of what is relevant for detection. Second, we generalize decorrelation to the multi-background setting, thus directly enforcing a more complete definition of robustness for anomaly detection. We demonstrate the benefit of the proposed robust multi-background anomaly detection algorithms on a high-dimensional dataset of particle decays at the Large Hadron Collider.
title Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning
topic High Energy Physics - Experiment
Machine Learning
High Energy Physics - Phenomenology
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2401.08777