A fast and flexible machine learning approach to data quality monitoring

TL;DR

This paper introduces a rapid, adaptable machine learning method for real-time data quality monitoring in particle detectors, utilizing kernel-based nonparametric algorithms to detect anomalies efficiently.

Contribution

It presents a novel, fast likelihood-ratio based approach using kernel methods for real-time data quality assessment in particle physics experiments.

Findings

Effective detection of anomalies in muon detector data

High computational efficiency and flexibility of the method

Model performance validated on multivariate detector data

Abstract

We present a machine learning based approach for real-time monitoring of particle detectors. The proposed strategy evaluates the compatibility between incoming batches of experimental data and a reference sample representing the data behavior in normal conditions by implementing a likelihood-ratio hypothesis test. The core model is powered by recent large-scale implementations of kernel methods, nonparametric learning algorithms that can approximate any continuous function given enough data. The resulting algorithm 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 a drift tube chambers muon detector.