← 研踪 PaperTrailarXiv:2611.05208 · v1
Privacy for Free in Efficient Agnostic Halfspace Learning
首次提交 2026-11-04 00:56
版本更新 2026-11-04 00:56
雷达观测 2026-11-04 23:39
摘要
We provide the first computationally efficient, differentially private algorithms for agnostically learning halfspaces. In particular, we study three different settings of agnostic learning: improper learning under Gaussian and log-concave marginals; proper learning under Gaussian marginals; and semi-agnostic learning under Gaussian marginals. In all three aforementioned settings, the added cost in the sample complexity due to privacy matches the respective non-private sample complexity, implying that we get privacy for free.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-04 00:56 · 最新观测版本
Privacy for Free in Efficient Agnostic Halfspace Learning
We provide the first computationally efficient, differentially private algorithms for agnostically learning halfspaces. In particular, we study three different settings of agnostic learning: improper learning under Gaussian and log-concave marginals; proper learning under Gaussian marginals; and semi-agnostic learning under Gaussian marginals. In all three aforementioned settings, the added cost in the sample complexity due to privacy matches the respective non-private sample complexity, implying that we get privacy for free.
查看此版本解读 →查看此版本原文 ↗