Beyond Square Roots: Explicit Memory-Efficient Factorization for Multi-Epoch Private Learning

Documenti analoghi

• Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGD
  di: Kalinin, Nikita P., et al.
  Pubblicazione: (2025)
• Banded Square Root Matrix Factorization for Differentially Private Model Training
  di: Kalinin, Nikita P., et al.
  Pubblicazione: (2024)
• On Optimal Hyperparameters for Differentially Private Deep Transfer Learning
  di: Rehn, Aki, et al.
  Pubblicazione: (2025)
• Learning Rate Scheduling with Matrix Factorization for Private Training
  di: Kalinin, Nikita P., et al.
  Pubblicazione: (2025)
• Mitigating Disparate Impact of Differentially Private Learning through Bounded Adaptive Clipping
  di: Zhao, Linzh, et al.
  Pubblicazione: (2025)