BOOST 2024 - 16th International Workshop on Boosted Object Phenomenology, Reconstruction, Measurements, and Searches at Colliders

Efficient machine learning for model-independent tests

31 lug 2024, 15:20

20m

Palazzo Ducale (Genova, Italy)

Talk Novel Techniques Novel Techniques

Relatore

Dr. Marco Letizia (Università di Genova and INFN)

Descrizione

The likelihood-ratio test can be used to perform a goodness-of-fit test between a reference model and observations if the alternative hypothesis is selected from data by exploring a rich parametrised family of functions. The New Physics Learning Machine (NPLM) methodology has been developed as a concrete realisation of this idea, to perform model-independent searches at collider experiments. In this presentation, I will focus on a recent implementation based on kernel methods, which is extremely efficient and highly flexible (arXiv:2204.02317). I will present studies on new physics searches, data quality monitoring, and recent results on the evaluation of generative models.