4 papers
Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise
Xinwen Zhang, Yihan Zhang, Heng Liang +1
Existing decentralized stochastic optimization methods assume the lower-level loss function is strongly convex and the stochastic gradient noise has finite variance. These strong a…
Federated Stochastic Minimax Optimization under Heavy-Tailed Noises
Xinwen Zhang, Hongchang Gao
Heavy-tailed noise has attracted growing attention in nonconvex stochastic optimization, as numerous empirical studies suggest it offers a more realistic assumption than standard b…
On Provable Benefits of Muon in Federated Learning
Xinwen Zhang, Hongchang Gao
The recently introduced optimizer, Muon, has gained increasing attention due to its superior performance across a wide range of applications. However, its effectiveness in federate…
Federated Compositional Deep AUC Maximization
Xinwen Zhang, Yihan Zhang, Tianbao Yang +2
Federated learning has attracted increasing attention due to the promise of balancing privacy and large-scale learning; numerous approaches have been proposed. However, most existi…