AI RESEARCH
Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing
arXiv CS.LG
•
ArXi:2605.20105v1 Announce Type: new Learning to generalise from limited data is a fundamental challenge for both artificial and biological systems. A common strategy is to extract reusable structure from abundant unlabelled data, enabling efficient adaptation to new tasks from limited labelled data. This two-stage paradigm is now standard in modern