研究人员开发了优化差分私有机器学习的新方法。一篇论文介绍了一种用于私有向量均值估计的感知混洗的优化方法，证明了在混洗后，标准的局部差分隐私机制可能不是最优的。另一项研究提出了一种使用随机投影的最优差分私有核学习算法，实现了极小极大最优的超额风险率。此外，第三篇论文分析了高维私有线性回归，表明诸如梯度裁剪和衰减学习率等实际算法选择可以带来最优的风险率。 AI
影响 这些论文推进了差分隐私在机器学习中的理论理解和实际应用，有望带来更强大、更安全的AI系统。
排序理由 该集群包含多篇学术论文，详细介绍了差分私有机器学习算法的进展和理论分析。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2604.28032v1 Announce Type: new Abstract: We study $d$-dimensional unbiased mean estimation in the single-message shuffle model, where each user sends a single privatized message and the analyzer only observes the shuffled multiset of reports. While minimax-optimal mechanis…
We study $d$-dimensional unbiased mean estimation in the single-message shuffle model, where each user sends a single privatized message and the analyzer only observes the shuffled multiset of reports. While minimax-optimal mechanisms are well understood in the local differential…
arXiv:2507.17544v4 Announce Type: replace Abstract: Differential privacy has become a cornerstone in the development of privacy-preserving learning algorithms. This work addresses optimizing differentially private kernel learning within the empirical risk minimization (ERM) frame…
arXiv:2505.16329v2 Announce Type: replace Abstract: Differentially private (DP) linear regression has received significant attention in the recent theoretical literature, with several approaches proposed to improve error rates. Our work considers the popular high-dimensional regi…