pac-bayes

Tag

Cards List
#pac-bayes

From Privacy to Generalization: Linear Max-Information Bounds for DP-SGD

arXiv cs.LG · 2026-05-27 Cached

This paper proves a finite-sample bound on the approximate max-information of DP-SGD that is at most linear in dataset size, yielding PAC-Bayes generalization bounds for models trained with differential privacy.

0 favorites 0 likes
#pac-bayes

Are Flat Minima an Illusion?

arXiv cs.LG · 2026-05-08 Cached

This paper challenges the common belief that flat minima cause better generalization in neural networks, arguing that 'weakness'—a reparameterization-invariant measure of function simplicity—is the true driver. Empirical results on MNIST and Fashion-MNIST show that weakness predicts generalization while sharpness anticorrelates, and the large-batch generalization advantage vanishes as training data increases.

0 favorites 0 likes
← Back to home

Submit Feedback