2 papers
hep-ph2026
Learning the Geometry of Collider Events with Metric-Aware Deep Sets
Lauren Hay, Rishabh Jain, Matt LeBlanc +1
Optimal transport gives structured data a geometry, but exact evaluation is costly in large pairwise analyses that exploit relationships among distances. Learned surrogates are fas…
physics.data-an2020
Explainable AI for ML jet taggers using expert variables and layerwise relevance propagation
Garvita Agarwal, Lauren Hay, Ia Iashvili +5
A framework is presented to extract and understand decision-making information from a deep neural network (DNN) classifier of jet substructure tagging techniques. The general metho…