Parts | Days | Selection | Search | Updates | Downloads | Help
T: Fachverband Teilchenphysik
T 93: Search for New Particles 6
T 93.5: Talk
Thursday, March 24, 2022, 17:15–17:30, T-H24
Better latent spaces for better autoencoders — Barry Dillon1, Tilman Plehn1, Christof Sauer2, and •Peter Sorrenson1,3 — 1Institut für Theoretische Physik, Universität Heidelberg, Germany — 2Physikalisches Institut, Universität Heidelberg, Germany — 3Heidelberg Collaboratory for Image Processing, Universität Heidelberg, Germany
Autoencoders as tools behind anomaly searches at the LHC have the structural problem that they only work in one direction, extracting jets with higher complexity but not the other way around. To address this, we derive classifiers from the latent space of (variational) autoencoders, specifically in Gaussian mixture and Dirichlet latent spaces. In particular, the Dirichlet setup solves the problem and improves both the performance and the interpretability of the networks.