SMuK 2023 – wissenschaftliches Programm

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

T: Fachverband Teilchenphysik

T 10: ML Methods I

T 10.6: Vortrag

Montag, 20. März 2023, 17:45–18:00, HSZ/0405

The Federation - A novel machine learning technique applied on data from the Higgs Boson Machine Learning Challenge — •Maximilian Mucha and Eckhard von Törne — Universität Bonn, Physikalisches Institut, Bonn, Germany

The Federation is a new machine learning technique for handling large amounts of data in a typical high-energy physics analysis. It utilizes Uniform Manifold Approximation and Projection (UMAP) to create an initial low-dimensional representation of a given data set, which is clustered by using Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). These clusters can then be used for a federated learning approach, in which we separately train a classifier on the high-dimensional data of each individual cluster. By doing so, the computational resource demands for the learning process is reduced. We additionally apply an imbalanced learning method to the data in the found clusters before the training to handle high class imbalances. By using a Dynamic Classifier Selection method, the Federation can then make predictions for the whole data set.

As a proof of concept for this novel technique, open data from the Higgs Boson Machine Learning Challenge is used and comparisons to results from established methods will be presented.