Poster
in
Workshop: High-dimensional Learning Dynamics Workshop: The Emergence of Structure and Reasoning

A Unified Approach to Feature Learning in Bayesian Neural Networks

Noa Rubin · Zohar Ringel · Inbar Seroussi · Moritz Helias

Project Page [ OpenReview]

Abstract

The power of neuronal networks comes from their adaptation to training data, known as feature learning. We consider feature learning within Bayesian learning and derive the two prominent high dimensional theories, kernel scaling and kernel adaptation, respectively, from a unified large deviation approach. We then show when feature learning escapes the scaling approach, but is captured by kernel adaptation.

Chat is not available.