New DP sampling method uses Wasserstein distance

Researchers have introduced a new framework for differentially private sampling from distributions, utilizing Wasserstein distance as the primary utility measure. This approach addresses limitations of prior methods that relied on KL divergence, particularly when dealing with differing distribution supports or when geometric structure is important. The proposed Wasserstein Projection Mechanism (WPM) is designed to be minimax optimal, with accompanying algorithms for approximate computation and convergence guarantees. AI

影响 Introduces a new privacy-preserving technique for sampling from distributions, potentially impacting the development of privacy-preserving machine learning models.

排序理由 Academic paper introducing a novel method for differentially private sampling. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

• Wasserstein distance
• Wasserstein Projection Mechanism

• 论文
• 安全

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →