Generalized Linear Bandits with Local Differential Privacy

06/07/2021
by   Yuxuan Han, et al.
0

Contextual bandit algorithms are useful in personalized online decision-making. However, many applications such as personalized medicine and online advertising require the utilization of individual-specific information for effective learning, while user's data should remain private from the server due to privacy concerns. This motivates the introduction of local differential privacy (LDP), a stringent notion in privacy, to contextual bandits. In this paper, we design LDP algorithms for stochastic generalized linear bandits to achieve the same regret bound as in non-privacy settings. Our main idea is to develop a stochastic gradient-based estimator and update mechanism to ensure LDP. We then exploit the flexibility of stochastic gradient descent (SGD), whose theoretical guarantee for bandit problems is rarely explored, in dealing with generalized linear bandits. We also develop an estimator and update mechanism based on Ordinary Least Square (OLS) for linear bandits. Finally, we conduct experiments with both simulation and real-world datasets to demonstrate the consistently superb performance of our algorithms under LDP constraints with reasonably small parameters (ε, δ) to ensure strong privacy protection.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/11/2021

Privacy Amplification via Shuffling for Linear Contextual Bandits

Contextual bandit algorithms are widely used in domains where it is desi...
research
06/07/2020

An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Sampling

We consider the contextual bandit problem, where a player sequentially m...
research
02/27/2023

On Differentially Private Federated Linear Contextual Bandits

We consider cross-silo federated linear contextual bandit (LCB) problem ...
research
02/11/2022

Shuffle Private Linear Contextual Bandits

Differential privacy (DP) has been recently introduced to linear context...
research
09/21/2020

Contextual Bandits for adapting to changing User preferences over time

Contextual bandits provide an effective way to model the dynamic data pr...
research
03/26/2020

A Principled Approach to Learning Stochastic Representations for Privacy in Deep Neural Inference

INFerence-as-a-Service (INFaaS) in the cloud has enabled the prevalent u...
research
04/13/2020

Power-Constrained Bandits

Contextual bandits often provide simple and effective personalization in...

Please sign up or login with your details

Forgot password? Click here to reset