A Generalization Theory for Zero-Shot Prediction

A modern paradigm for generalization in machine learning and AI consists of pre-training a task-agnostic foundation model, generally obtained using self-supervised and multimodal contrastive learning. The resulting representations can be used for prediction on a downstream task for which no labeled data is available. We present a theoretical framework to better understand this approach, called zero-shot prediction. We identify the target quantities that zeroshot prediction aims to learn, or learns in passing, and the key conditional independence relationships that enable its generalization ability.