High-dimensional and Permutation Invariant Anomaly Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mikuni, Vinicius, Nachman, Benjamin
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914702962982912
author Mikuni, Vinicius
Nachman, Benjamin
author_facet Mikuni, Vinicius
Nachman, Benjamin
contents Methods for anomaly detection of new physics processes are often limited to low-dimensional spaces due to the difficulty of learning high-dimensional probability densities. Particularly at the constituent level, incorporating desirable properties such as permutation invariance and variable-length inputs becomes difficult within popular density estimation methods. In this work, we introduce a permutation-invariant density estimator for particle physics data based on diffusion models, specifically designed to handle variable-length inputs. We demonstrate the efficacy of our methodology by utilizing the learned density as a permutation-invariant anomaly detection score, effectively identifying jets with low likelihood under the background-only hypothesis. To validate our density estimation method, we investigate the ratio of learned densities and compare to those obtained by a supervised classification algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2306_03933
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle High-dimensional and Permutation Invariant Anomaly Detection
Mikuni, Vinicius
Nachman, Benjamin
High Energy Physics - Phenomenology
Artificial Intelligence
Machine Learning
High Energy Physics - Experiment
Methods for anomaly detection of new physics processes are often limited to low-dimensional spaces due to the difficulty of learning high-dimensional probability densities. Particularly at the constituent level, incorporating desirable properties such as permutation invariance and variable-length inputs becomes difficult within popular density estimation methods. In this work, we introduce a permutation-invariant density estimator for particle physics data based on diffusion models, specifically designed to handle variable-length inputs. We demonstrate the efficacy of our methodology by utilizing the learned density as a permutation-invariant anomaly detection score, effectively identifying jets with low likelihood under the background-only hypothesis. To validate our density estimation method, we investigate the ratio of learned densities and compare to those obtained by a supervised classification algorithm.
title High-dimensional and Permutation Invariant Anomaly Detection
topic High Energy Physics - Phenomenology
Artificial Intelligence
Machine Learning
High Energy Physics - Experiment
url https://arxiv.org/abs/2306.03933