14–18 Sept 2026
Europe/Vienna timezone

Information Geometry of Latent Representations for Interpretable Jet Tagging

16 Sept 2026, 15:00
20m

Speaker

Benedikt Schosser

Description

Latent representations are an important theme in modern machine learning. While information geometry provides a framework to analyze their structure, it also offers new insight into the physics learned by jet-tagging networks. We apply these methods to binary quark-gluon classification and three-fold fat-jet tagging and relate the learned latent representation to characteristic features of QCD radiation and heavy-particle decays. We show how information-geometric observables identify the relevant physics encoded by the network and connect the classifier’s decisions to established jet observables.

Authors

Benedikt Schosser Björn Malte Schäfer Rebecca Maria Wolfgramm-Kuntz (Astronomisches Rechen-Institut, Zentrum für Astronomie, Universität Heidelberg) Sophia Vent Tilman Plehn

Presentation materials

There are no materials yet.