Saved in:
Bibliographic Details
Main Authors: Zhou, Mo, Ge, Rong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.01766
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • The ability of learning useful features is one of the major advantages of neural networks. Although recent works show that neural network can operate in a neural tangent kernel (NTK) regime that does not allow feature learning, many works also demonstrate the potential for neural networks to go beyond NTK regime and perform feature learning. Recently, a line of work highlighted the feature learning capabilities of the early stages of gradient-based training. In this paper we consider another mechanism for feature learning via gradient descent through a local convergence analysis. We show that once the loss is below a certain threshold, gradient descent with a carefully regularized objective will capture ground-truth directions. We further strengthen this local convergence analysis by incorporating early-stage feature learning analysis. Our results demonstrate that feature learning not only happens at the initial gradient steps, but can also occur towards the end of training.