FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models

Documenti analoghi

• DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Models
  di: Liu, Jin, et al.
  Pubblicazione: (2026)
• FedNSAM:Consistency of Local and Global Flatness for Federated Learning
  di: Liu, Junkang, et al.
  Pubblicazione: (2026)
• FedMuon: Accelerating Federated Learning with Matrix Orthogonalization
  di: Liu, Junkang, et al.
  Pubblicazione: (2025)
• FedBCD:Communication-Efficient Accelerated Block Coordinate Gradient Descent for Federated Learning
  di: Liu, Junkang, et al.
  Pubblicazione: (2026)
• DP-FedPGN: Finding Global Flat Minima for Differentially Private Federated Learning via Penalizing Gradient Norm
  di: Liu, Junkang, et al.
  Pubblicazione: (2025)