Speaker
Dr
Marco Letizia
Description
We present a machine learning approach for real-time detector monitoring. The corresponding core algorithm is powered by recent large-scale implementations of kernel methods, nonparametric learning algorithms that can approximate any continuous function given enough data. The model evaluates the compatibility between incoming batches of experimental data and a reference data sample, by implementing a hypothesis testing procedure based on the likelihood ratio. The resulting model is fast, efficient and agnostic about the type of potential anomaly in the data. We show the performance of the model on multivariate data from muon chamber monitoring.
Authors
Andrea Wulzer
(CERN and EPFL)
Gaia Grosso
(Universita e INFN, Padova (IT))
Jacopo Pazzini
(Università e INFN, Padova (IT))
Dr
Marco Letizia
Marco Rando
(Universita` degli Studi di Genova)
Marco Zanetti
(Universita e INFN, Padova (IT))
Mr
Nicolò Lai
(Università di Padova)
