Skip to Main content Skip to Navigation
Poster communications

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.
Complete list of metadata

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/hal-02428005
Contributor : Cecile Germain <>
Submitted on : Saturday, January 4, 2020 - 6:10:40 PM
Last modification on : Sunday, May 2, 2021 - 3:30:22 AM
Long-term archiving on: : Monday, April 6, 2020 - 8:46:58 PM

File

NeurIPS_ML4PS_2019_36.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02428005, version 1

Citation

Adrian 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⟩

Share

Metrics

Record views

103

Files downloads

263