Speaker
Zihan Zhao
(Univ. of California San Diego (US))
Description
Limited by the lack of truth labels on real data, fully supervised ML algorithms are constrained to training only with simulated samples. With self-supervised learning, we can leverage vast amounts of unlabeled real data to facilitate training. We investigate the application of VICReg, a contrastive learning model, on a classification task: discriminating signal jets (e.g. $H \rightarrow b \bar{b}$ jets) from background jets (e.g. QCD jets). We also explore the use of jet augmentations in contrastive learning.
Authors
Carlos Pareja
(University of California, San Diego)
Farouk Mokhtar
(Univ. of California San Diego (US))
Javier Mauricio Duarte
(Univ. of California San Diego (US))
Raghav Kansal
(Univ. of California San Diego (US))
Zihan Zhao
(Univ. of California San Diego (US))
