Provable Privacy Advantages of Decentralized Federated Learning via Distributed Optimization

Documenti analoghi

• Byzantine-Resilient Federated Learning via Distributed Optimization
  di: Xia, Yufei, et al.
  Pubblicazione: (2025)
• Privacy-Preserving Distributed Maximum Consensus Without Accuracy Loss
  di: Yu, Wenrui, et al.
  Pubblicazione: (2024)
• Adaptive Differentially Quantized Subspace Perturbation (ADQSP): A Unified Framework for Privacy-Preserving Distributed Average Consensus
  di: Li, Qiongxiu, et al.
  Pubblicazione: (2023)
• When Is Distributed Nonlinear Aggregation Private? Optimality and Information-Theoretical Bounds
  di: Yu, Wenrui, et al.
  Pubblicazione: (2026)
• From Centralized to Decentralized Federated Learning: Theoretical Insights, Privacy Preservation, and Robustness Challenges
  di: Li, Qiongxiu, et al.
  Pubblicazione: (2025)