Differentially-Private Federated Linear Bandits

Abstract

The rapid proliferation of decentralized learning systems mandates the need for differentially-private cooperative learning. In this paper, we study this in context of the contextual linear bandit: we consider a collection of agents cooperating to solve a common contextual bandit, while ensuring that their communication remains private. For this problem, we devise \textsc{FedUCB}, a multiagent private algorithm for both centralized and decentralized (peer-to-peer) federated learning. We provide a rigorous technical analysis of its utility in terms of regret, improving several results in cooperative bandit learning, and provide rigorous privacy guarantees as well. Our algorithms provide competitive performance both in terms of pseudoregret bounds and empirical benchmark performance in various multi-agent settings.

arXiv comment22 pages. Camera-ready for NeurIPS 2020

References in corpus (14)

• Federated Learning: Strategies for Improving Communication Efficiency
• A Contextual-Bandit Approach to Personalized News Article Recommendation
• Analysis of Thompson Sampling for the multi-armed bandit problem
• Differentially Private Federated Learning: A Client Level Perspective
• Distributed Learning in Multi-Armed Bandit with Multiple Players
• Further Optimal Regret Bounds for Thompson Sampling
• Finite-Time Analysis of Kernelised Contextual Bandits
• Distributed Clustering of Linear Bandits in Peer to Peer Networks
• Local Differential Privacy and Its Applications: A Comprehensive Survey
• Differentially Private Contextual Linear Bandits
• Data Cooperatives: Towards a Foundation for Decentralized Personal Data Management
• Privacy-Preserving Multi-Party Contextual Bandits
• Kernel Methods for Cooperative Multi-Agent Contextual Bandits
• Cooperative Multi-Agent Bandits with Heavy Tails

Cited by in corpus (10)

• Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligence
• Federated Bandit: A Gossiping Approach
• Multi-Agent Multi-Armed Bandits with Limited Communication
• Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits
• Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits
• Dynamic Global Sensitivity for Differentially Private Contextual Bandits
• Local Differential Privacy for Regret Minimization in Reinforcement Learning
• PPT: A Privacy-Preserving Global Model Training Protocol for Federated Learning in P2P Networks
• Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee
• Decentralized Upper Confidence Bound Algorithms for Homogeneous Multi-Agent Multi-Armed Bandits