Distributionally Robust Federated Learning with Multi-Source Data
A global ambiguity set is constructed as the union of admissible mixtures of local ambiguity sets that allows client-specific ambiguity radii and admits a client-wise separable reformulation and establishes a high-probability out-of-sample performance guarantee.
Ying-Zhu Liu, Zhong-Kui Li, Peng-Cheng You et al.
· 0 citations