# A Generalization Theory for Zero-Shot Prediction

arXiv: https://arxiv.org/abs/2507.09128 · HTML: https://mlsanity.com/paper/2507.09128/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2025.

## Built on by (most cited first, 3 of 3)

- [Adapting Time Series Foundation Models through Data Mixtures](https://mlsanity.com/paper/2603.02840/) (2026)
- [Machine Learning for Underwater Optical Wireless Communication Systems: A Comprehensive Survey](https://mlsanity.com/paper/2609.22294/) (2026)
- [Multi-Marginal Inverse Optimal Transport for Contrastive Learning Via Explicit Anchor-Positive-Negative Coupling](https://mlsanity.com/paper/2609.33741/) (2026)

## Abstract (arXiv)

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 zero-shot prediction aims to learn, or learns in passing, and the key conditional independence relationships that enable its generalization ability.