Resonant Anomaly Detection with Multiple Reference Datasets

12/20/2022
by   Mayee F. Chen, et al.
0

An important class of techniques for resonant anomaly detection in high energy physics builds models that can distinguish between reference and target datasets, where only the latter has appreciable signal. Such techniques, including Classification Without Labels (CWoLa) and Simulation Assisted Likelihood-free Anomaly Detection (SALAD) rely on a single reference dataset. They cannot take advantage of commonly-available multiple datasets and thus cannot fully exploit available information. In this work, we propose generalizations of CWoLa and SALAD for settings where multiple reference datasets are available, building on weak supervision techniques. We demonstrate improved performance in a number of settings with realistic and synthetic data. As an added benefit, our generalizations enable us to provide finite-sample guarantees, improving on existing asymptotic analyses.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/06/2021

New Methods and Datasets for Group Anomaly Detection From Fundamental Physics

The identification of anomalous overdensities in data - group or collect...
research
09/04/2020

Simulation-Assisted Decorrelation for Resonant Anomaly Detection

A growing number of weak- and unsupervised machine learning approaches t...
research
04/19/2022

"Flux+Mutability": A Conditional Generative Approach to One-Class Classification and Anomaly Detection

Anomaly Detection is becoming increasingly popular within the experiment...
research
03/21/2023

Defect Detection Approaches Based on Simulated Reference Image

This work is addressing the problem of defect anomaly detection based on...
research
06/16/2023

Flow-Bench: A Dataset for Computational Workflow Anomaly Detection

A computational workflow, also known as workflow, consists of tasks that...
research
02/21/2022

Composite Anomaly Detection via Hierarchical Dynamic Search

Anomaly detection among a large number of processes arises in many appli...
research
07/03/2023

Application of MUSIC-type imaging for anomaly detection without background information

It has been demonstrated that the MUltiple SIgnal Classification (MUSIC)...

Please sign up or login with your details

Forgot password? Click here to reset