Do you pay for Privacy in Online learning?
Machine Learning
2022-10-11 v1 Cryptography and Security
Abstract
Online learning, in the mistake bound model, is one of the most fundamental concepts in learning theory. Differential privacy, instead, is the most widely used statistical concept of privacy in the machine learning community. It is thus clear that defining learning problems that are online differentially privately learnable is of great interest. In this paper, we pose the question on if the two problems are equivalent from a learning perspective, i.e., is privacy for free in the online learning framework?
Keywords
Cite
@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}
}
Comments
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