George Deligiannidis

Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks

2020 · HAL (Le Centre pour la Communication Scientifique Directe)

Despite its success in a wide range of applications, characterizing the generalization properties of stochastic gradient descent (SGD) in non-convex deep learning problems is still an important challenge. While modeling the trajectories of SGD via …

Generalisation under gradient descent via deterministic PAC-Bayes

2022 · arXiv (Cornell University)

We establish disintegrated PAC-Bayesian generalisation bounds for models trained with gradient descent methods or continuous gradient flows. Contrary to standard practice in the PAC-Bayesian setting, our result applies to optimisation algorithms that are deterministic, without …