On Mitigating the Utility-Loss in Differentially Private Learning: A new Perspective by a Geometrically Inspired Kernel Approach

Documenti analoghi

• Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off
  di: Li, Yuecheng, et al.
  Pubblicazione: (2024)
• Differentially Private Deep Model-Based Reinforcement Learning
  di: Rio, Alexandre, et al.
  Pubblicazione: (2024)
• Differentially Private In-Context Learning with Nearest Neighbor Search
  di: Koskela, Antti, et al.
  Pubblicazione: (2025)
• Differentially Private Model Merging
  di: Yin, Qichuan, et al.
  Pubblicazione: (2026)
• Differentially Private Block-wise Gradient Shuffle for Deep Learning
  di: Zagardo, David
  Pubblicazione: (2024)