Null hypothesis test for anomaly detection

• Autores: Kamenik, Jernej F.; Szewc, Manuel
• Año de publicación: 2023
• Idioma: inglés
• Tipo de recurso: artículo
• Materia: LHC; ANOMALY DETECTION; CWOLA; UNSUPERVISED
• Institución: Consejo Nacional de Investigaciones Científicas y Técnicas

We extend the use of Classification Without Labels for anomaly detection with a hypothesis test designed to exclude the background-only hypothesis. By testing for statistical independence of the two discriminating dataset regions, we are able to exclude the background-only hypothesis without relying on fixed anomaly score cuts or extrapolations of background estimates between regions. The method relies on the assumption of conditional independence of anomaly score features and dataset regions, which can be ensured using existing decorrelation techniques. As a benchmark example, we consider the LHC Olympics dataset where we show that mutual information represents a suitable test for statistical independence and our method exhibits excellent and robust performance at different signal fractions even in presence of realistic feature correlations.
Fil: Kamenik, Jernej F.. University of Ljubljana; Eslovenia
Fil: Szewc, Manuel. University of Ljubljana; Eslovenia. Consejo Nacional de Investigaciones Científicas y Técnicas. Instituto de Ciencias Físicas. - Universidad Nacional de San Martín. Instituto de Ciencias Físicas; Argentina