Speaker
Jeffrey Krupa
(Massachusetts Institute of Technology)
Description
Self-Supervised Learning (SSL) is at the core of training modern large ML models, providing a scheme for learning powerful representations in base models that can be used in a variety of downstream tasks. However, SSL training strategies must be adapted to the type of training data, thus driving the question: what are powerful SSL strategies for collider physics data? In the talk, we present a novel re-simulation-based SSL (RS3L) strategy wherein we develop a method of “re-simulation” to drive data augmentation for contrastive learning. We show how a RS3L-trained base model can learn powerful representations that can be used for downstream discrimination tasks and can help mitigate uncertainties.
Authors
Benedikt Maier
(KIT - Karlsruhe Institute of Technology (DE))
Jeffrey Krupa
(Massachusetts Institute of Technology)
Maurizio Pierini
(CERN)
Michael Kagan
(SLAC National Accelerator Laboratory (US))
Nathaniel Sherlock Woodward
(Massachusetts Inst. of Technology (US))
Philip Coleman Harris
(Massachusetts Inst. of Technology (US))
