activity
20242026
most citedUnderstanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees

1 citations · 1 across the 7 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.LG2026

Mitigating the Curse of Dimensionality in Uniform Convergence of Deep Neural Networks via Smooth Activations

Yizhe Ding, Runze Li, Jia Liu +1

This paper establishes a theoretical framework for the uniform convergence of smoothly activated deep neural network (DNN) estimators. While standard ReLU networks achieve minimax-…