3 citations · 6 across the 5 of their papers we have counts for
3 papers · 1 filter
Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD
Yijun Wan, Melih Barsbey, Abdellatif Zaidi +1
Neural network compression has been an increasingly important subject, not only due to its practical relevance, but also due to its theoretical implications, as there is an explici…
Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often!
Milad Sefidgaran, Romain Chor, Abdellatif Zaidi +1
We investigate the generalization error of statistical learning models in a Federated Learning (FL) setting. Specifically, we study the evolution of the generalization error with t…
Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent
Soon Hoe Lim, Yijun Wan, Umut Şimşekli
Recent studies have shown that gradient descent (GD) can achieve improved generalization when its dynamics exhibits a chaotic behavior. However, to obtain the desired effect, the s…