在线学习中你是否为隐私付出代价?
机器学习
2022-10-11 v1 密码学与安全
摘要
错误界模型下的在线学习是学习理论中最基本的概念之一。而差分隐私是机器学习界使用最广泛的隐私统计概念。因此,定义可在线差分隐私学习的机器学习问题显然具有重大意义。在本文中,我们提出这样一个问题:从学习视角看这两个问题是否等价,即在在线学习框架中隐私是否是免费的?
引用
@article{arxiv.2210.04817,
title = {Do you pay for Privacy in Online learning?},
author = {Amartya Sanyal and Giorgia Ramponi},
journal= {arXiv preprint arXiv:2210.04817},
year = {2022}
}
备注
This is an updated version with i) clearer problem statements especially in proposed Theorem 1 and ii) clearer discussion of existing work especially Golowich and Livni (2021). Conference on Learning Theory. PMLR, 2022