Efficient Private Algorithms for Learning Halfspaces.
arXiv: Learning(2019)
摘要
We present new differentially private algorithms for learning a large-margin halfspace. In contrast to previous algorithms, which are based on either differentially private simulations of the statistical query model or on private convex optimization, the sample complexity of our algorithms depends only on the margin of the data, and not on the dimension.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络