Speakers
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 simulation-based SSL (S3L) strategy wherein we develop a method of “re-simulation” to drive data augmentation for contrastive learning. We show how an S3L-trained base model can learn powerful representations that can be used for downstream discrimination tasks and can help mitigate uncertainties.
Brainstorming idea [abstract]
Which is the best way to learn powerful representations of HEP data, and what are its most promising applications? We will brainstorm about HEP-typical problems like classification, regression, and clustering and how self-supervised learning strategies can help solving them.
Brainstorming idea [title] | What are the right SSL strategies for HEP data? |
---|