arXiv · 2603.02310
The Latent Information Geometry of Jet Classification
Abstract
Latent representations are an important theme in modern machine learning. Any network training with the notion of locality introduces a latent geometry which we can analyze with the help of differential geometry, specifically information geometry. We introduce the main concepts needed to analyze learned latent geometries, specifically curvature and nonmetricities, and show how they can be used for decoder and classifier geometries. We then apply our new methods to understand the physics behind binary quark-gluon classification and three-fold fat jet tagging.
Explore related subjects
Keep this discovery
Rebecca Maria Kuntz, Tilman Plehn, Björn Malte Schäfer, Benedikt Schosser, Sophia Vent. 2026-03-02. The Latent Information Geometry of Jet Classification. https://arxiv.org/abs/2603.02310
Cite the original work for its findings. Save a collection to share your selection of sources.