Key points are not available for this paper at this time.
There has been considerable effort to better understand the generalization capabilities of deep neural networks both as a means to unlock a theoretical understanding of their success as well as providing directions for further improvements. In this paper, we investigate margin-based multiclass generalization bounds for neural networks which rely on a recent complexity measure, the geometric complexity, developed for neural networks. We derive a new upper bound on the generalization error which scales with the margin-normalized geometric complexity of the network and which holds for a broad family of data distributions and model classes. Our generalization bound is empirically investigated for a ResNet-18 model trained with SGD on the CIFAR-10 and CIFAR-100 datasets with both original and random labels.
Building similarity graph...
Analyzing shared references across papers
Loading...
Munn et al. (Tue,) studied this question.
synapsesocial.com/papers/68e68232b6db64358760b9d5 — DOI: https://doi.org/10.48550/arxiv.2405.18590
Michael Munn
Karlsruhe Institute of Technology
Benoît Dherin
Google (United States)
Javier Gonzalvo
Google (United States)
Building similarity graph...
Analyzing shared references across papers
Loading...