Trigger Rate Anomaly Detection with Conditional Variational Autoencoders at the CMS Experiment - Laboratoire Interdisciplinaire des Sciences du Numérique Access content directly
Conference Papers Year : 2019

Trigger Rate Anomaly Detection with Conditional Variational Autoencoders at the CMS Experiment

Abstract

Exploiting the rapid advances in probabilistic inference, in particular variational autoencoders (VAEs) for machine learning (ML) anomaly detection (AD) tasks, remains an open research question. In this work, we use the deep conditional varia-tional autoencoders (CVAE), and we define an original loss function together with a metric that targets AD for hierarchically structured data. Our target application is a real world problem: monitoring the trigger system which is a component of many particle physics experiments at the CERN Large Hadron Collider (LHC). Experiments show the superior performance of this method over vanilla VAEs.
Fichier principal
Vignette du fichier
NeurIPS_ML4PS_2019_36.pdf (348.16 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02428005 , version 1 (04-01-2020)

Identifiers

  • HAL Id : hal-02428005 , version 1

Cite

Adrian Alan Pol, Victor Berger, Gianluca Cerminara, Cécile Germain, Maurizio Pierini. Trigger Rate Anomaly Detection with Conditional Variational Autoencoders at the CMS Experiment. Machine Learning and the Physical Sciences Workshop at the 33rd Conference on Neural Information Processing Systems (NeurIPS), Dec 2019, Vancouver, Canada. ⟨hal-02428005⟩
155 View
138 Download

Share

Gmail Facebook X LinkedIn More