Variance Reduced Distributed Non-Convex Optimization Using Matrix Stepsizes

Documenti analoghi

• Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization
  di: Li, Hanmin, et al.
  Pubblicazione: (2023)
• SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning
  di: Karagulyan, Avetik, et al.
  Pubblicazione: (2024)
• On the Convergence of FedProx with Extrapolation and Inexact Prox
  di: Li, Hanmin, et al.
  Pubblicazione: (2024)
• Stabilized Proximal Point Method via Trust Region Control
  di: Li, Hanmin, et al.
  Pubblicazione: (2026)
• The Power of Extrapolation in Federated Learning
  di: Li, Hanmin, et al.
  Pubblicazione: (2024)