representation-gap

Tag

Cards List
#representation-gap

Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective

arXiv cs.LG · 2026-05-22 Cached

This paper introduces the Representation Gap, a metric for neural network generalization error with better asymptotic dynamics. Using a geometric perspective and optimal quantization theory, the authors show it is governed by the intrinsic dimension of the task, and verify this empirically on synthetic and realistic datasets.

0 favorites 0 likes
← Back to home

Submit Feedback