Noise is All You Need: Private Second-Order Convergence of Noisy SGD

Documenti analoghi

• Finding Differentially Private Second Order Stationary Points in Stochastic Minimax Optimization
  di: Xu, Difei, et al.
  Pubblicazione: (2026)
• Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training
  di: Sander, Tom, et al.
  Pubblicazione: (2024)
• PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance
  di: Sha, Haichao, et al.
  Pubblicazione: (2023)
• RQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization
  di: Feng, Ce, et al.
  Pubblicazione: (2024)
• Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness
  di: Chien, Eli, et al.
  Pubblicazione: (2024)