Do you pay for Privacy in Online learning?
This addresses a foundational question for researchers in learning theory and privacy, potentially impacting the design of private online algorithms.
The paper investigates whether differential privacy can be achieved without additional cost in the online learning mistake bound model, aiming to determine if privacy is free in this framework.
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?