The Price of Differential Privacy For Online Learning

01/27/2017
by   Naman Agarwal, et al.
0

We design differentially private algorithms for the problem of online linear optimization in the full information and bandit settings with optimal Õ(√(T)) regret bounds. In the full-information setting, our results demonstrate that ϵ-differential privacy may be ensured for free -- in particular, the regret bounds scale as O(√(T))+Õ(1/ϵ). For bandit linear optimization, and as a special case, for non-stochastic multi-armed bandits, the proposed algorithm achieves a regret of Õ(1/ϵ√(T)), while the previously known best regret bound was Õ(1/ϵT^2/3).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/07/2022

Differentially Private Stochastic Linear Bandits: (Almost) for Free

In this paper, we propose differentially private algorithms for the prob...
research
09/28/2018

Differentially Private Contextual Linear Bandits

We study the contextual linear bandit problem, a version of the standard...
research
01/16/2017

Achieving Privacy in the Adversarial Multi-Armed Bandit

In this paper, we improve the previously best known regret bound to achi...
research
12/09/2022

Near-Optimal Differentially Private Reinforcement Learning

Motivated by personalized healthcare and other applications involving se...
research
09/01/2011

Differentially Private Online Learning

In this paper, we consider the problem of preserving privacy in the onli...
research
06/27/2022

Differentially Private Federated Combinatorial Bandits with Constraints

There is a rapid increase in the cooperative learning paradigm in online...
research
01/29/2023

Concurrent Shuffle Differential Privacy Under Continual Observation

We introduce the concurrent shuffle model of differential privacy. In th...

Please sign up or login with your details

Forgot password? Click here to reset