Murat A. Erdogdu

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 …

Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks.

2021 · HAL (Le Centre pour la Communication Scientifique Directe)

International audience