Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGD

Documenti analoghi

• Normalized Square Root: Sharper Matrix Factorization Bounds for Differentially Private Continual Counting
  di: Henzinger, Monika, et al.
  Pubblicazione: (2025)
• Banded Square Root Matrix Factorization for Differentially Private Model Training
  di: Kalinin, Nikita P., et al.
  Pubblicazione: (2024)
• Scaling up the Banded Matrix Factorization Mechanism for Differentially Private ML
  di: McKenna, Ryan
  Pubblicazione: (2024)
• Almost Tight Error Bounds on Differentially Private Continual Counting
  di: Henzinger, Monika, et al.
  Pubblicazione: (2022)
• DP-KAN: Differentially Private Kolmogorov-Arnold Networks
  di: Kalinin, Nikita P., et al.
  Pubblicazione: (2024)