Adaptive Mean Estimation by In-Context Learning: A Gradient-Flow Analysis

Excerpt

arXiv:2610.07804v1 Announce Type: new Abstract: Prior Fitted Networks (PFNs) such as TabPFN now rival established statistical procedures across prediction and estimation tasks. A natural explanation is that PFNs have the property of statistical adaptivity, that is, they perform nearly as well as a method tailored to the true data-generating model for a heterogeneous set of models, while not being told which model the data comes from. We study how such adaptivity is learned in a controlled locati