Challenges for Unsupervised Anomaly Detection in Particle Physics

10/13/2021
by   Katherine Fraser, et al.
0

Anomaly detection relies on designing a score to determine whether a particular event is uncharacteristic of a given background distribution. One way to define a score is to use autoencoders, which rely on the ability to reconstruct certain types of data (background) but not others (signals). In this paper, we study some challenges associated with variational autoencoders, such as the dependence on hyperparameters and the metric used, in the context of anomalous signal (top and W) jets in a QCD background. We find that the hyperparameter choices strongly affect the network performance and that the optimal parameters for one signal are non-optimal for another. In exploring the networks, we uncover a connection between the latent space of a variational autoencoder trained using mean-squared-error and the optimal transport distances within the dataset. We then show that optimal transport distances to representative events in the background dataset can be used directly for anomaly detection, with performance comparable to the autoencoders. Whether using autoencoders or optimal transport distances for anomaly detection, we find that the choices that best represent the background are not necessarily best for signal identification. These challenges with unsupervised anomaly detection bolster the case for additional exploration of semi-supervised or alternative approaches.

READ FULL TEXT

page 8

page 9

page 14

page 15

page 16

research
11/11/2021

Online-compatible Unsupervised Non-resonant Anomaly Detection

There is a growing need for anomaly detection methods that can broaden t...
research
09/29/2020

A comparison of classical and variational autoencoders for anomaly detection

This paper analyzes and compares a classical and a variational autoencod...
research
10/05/2022

Null Hypothesis Test for Anomaly Detection

We extend the use of Classification Without Labels for anomaly detection...
research
08/04/2022

Background Modeling for Double Higgs Boson Production: Density Ratios and Optimal Transport

We study the problem of data-driven background estimation, arising in th...
research
04/19/2021

Autoencoders for unsupervised anomaly detection in high energy physics

Autoencoders are widely used in machine learning applications, in partic...
research
03/29/2022

Radial Autoencoders for Enhanced Anomaly Detection

In classification problems, supervised machine-learning methods outperfo...
research
10/12/2020

Anomaly Detection With Conditional Variational Autoencoders

Exploiting the rapid advances in probabilistic inference, in particular ...

Please sign up or login with your details

Forgot password? Click here to reset