Heidelberg 2022 – scientific program
T 93.1: Talk
Thursday, March 24, 2022, 16:15–16:30, T-H24
Symmetries, Safety, and Self-Supervision — Barry M. Dillon1, Gregor Kasieczka2, Hans Olischläger1, Tilman Plehn1, Peter Sorrenson1,3, and •Lorenz Vogel1 — 1Institut für Theoretische Physik, Universität Heidelberg, Germany — 2Institut für Experimentalphysik, Universität Hamburg, Germany — 3Heidelberg Collaboratory for Image Processing, Universität Heidelberg, Germany
Collider searches face the challenge of defining a representation of high-dimensional data such that physical symmetries are manifest, the discriminating features are retained, and the choice of representation is data-driven and new-physics agnostic. We introduce JetCLR (Contrastive Learning of Jet Representations) to solve the mapping from low-level jet constituent data to optimized observables through self-supervised contrastive learning. Using a permutation-invariant transformer-encoder network, physical symmetries such as rotations and translations are encoded as augmentations in a contrastive learning framework. As an example, we construct a data representation for top and QCD jets and visualize its symmetry properties. We benchmark the JetCLR representation against other widely-used jet representations, such as jet images and energy flow polynomials.