Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data

Documenti analoghi

• Revisiting ML Training under Fully Homomorphic Encryption: Convergence Guarantees, Differential Privacy, and Efficient Algorithms
  di: Zhou, Yvonne, et al.
  Pubblicazione: (2026)
• Balancing Fairness and Accuracy in Data-Restricted Binary Classification
  di: Lazri, Zachary McBride, et al.
  Pubblicazione: (2024)
• DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharing
  di: Bienstock, Alexander, et al.
  Pubblicazione: (2024)
• TAPAS: Efficient Two-Server Asymmetric Private Aggregation Beyond Prio(+)
  di: Karthikeyan, Harish, et al.
  Pubblicazione: (2026)
• A Canonical Data Transformation for Achieving Inter- and Within-group Fairness
  di: Lazri, Zachary McBride, et al.
  Pubblicazione: (2023)