Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Machine Learning and the Physical Sciences

G-SpaNet: Generalized Permutationless Set Assignment for Particle Physics using Symmetry Preserving Attention

Alexander Shmakov · Shih-chieh Hsu · Pierre Baldi


Abstract:

We introduce a novel method for constructing symmetry-preserving attention networks which reflect the natural invariances of the jet-parton assignment problem to efficiently find assignments without evaluating all permutations. This general approach is applicable to arbitrarily complex configurations and significantly outperforms current methods, improving reconstruction efficiency between 19% - 35% on benchmark problems while decreasing inference time by two to five orders of magnitude, making many important and previously intractable cases tractable.

Chat is not available.