Revisiting ML Training under Fully Homomorphic Encryption: Convergence Guarantees, Differential Privacy, and Efficient Algorithms

Documenti analoghi

• Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data
  di: Zhou, Yvonne, et al.
  Pubblicazione: (2024)
• Balancing Fairness and Accuracy in Data-Restricted Binary Classification
  di: Lazri, Zachary McBride, et al.
  Pubblicazione: (2024)
• A Canonical Data Transformation for Achieving Inter- and Within-group Fairness
  di: Lazri, Zachary McBride, et al.
  Pubblicazione: (2023)
• MAFE: Enabling Equitable Algorithm Design in Multi-Agent Multi-Stage Decision-Making Systems
  di: Lazri, Zachary McBride, et al.
  Pubblicazione: (2025)
• Atlas-X Equity Financing: Unlocking New Methods to Securely Obfuscate Axe Inventory Data Based on Differential Privacy
  di: Polychroniadou, Antigoni, et al.
  Pubblicazione: (2024)