most citedZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learning

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2025

The Mathematical Theory of Double Descent as Shrinkage, not Overfitting: Matching Bounds for Path-Regularized Multilayer Neural Networks

Hao Yu

We give a nonasymptotic generalization theory for multilayer fully connected neural networks trained with path regularization, for general Lipschitz losses and without assuming the…