DeepAI AI Chat
Log In Sign Up

Byzantine-Robust Federated Linear Bandits

04/03/2022
βˆ™
by   Ali Jadbabaie, et al.
βˆ™
MIT
βˆ™
9
βˆ™

In this paper, we study a linear bandit optimization problem in a federated setting where a large collection of distributed agents collaboratively learn a common linear bandit model. Standard federated learning algorithms applied to this setting are vulnerable to Byzantine attacks on even a small fraction of agents. We propose a novel algorithm with a robust aggregation oracle that utilizes the geometric median. We prove that our proposed algorithm is robust to Byzantine attacks on fewer than half of agents and achieves a sublinear π’ͺΜƒ(T^3/4) regret with π’ͺ(√(T)) steps of communication in T steps. Moreover, we make our algorithm differentially private via a tree-based mechanism. Finally, if the level of corruption is known to be small, we show that using the geometric median of mean oracle for robust aggregation further improves the regret bound.

READ FULL TEXT

page 1

page 2

page 3

page 4

βˆ™ 10/22/2020

Differentially-Private Federated Linear Bandits

The rapid proliferation of decentralized learning systems mandates the n...
βˆ™ 09/11/2019

Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging

Federated learning enables training collaborative machine learning model...
βˆ™ 04/27/2023

Attacks on Robust Distributed Learning Schemes via Sensitivity Curve Maximization

Distributed learning paradigms, such as federated or decentralized learn...
βˆ™ 12/31/2019

Robust Aggregation for Federated Learning

We present a robust aggregation approach to make federated learning robu...
βˆ™ 05/09/2022

Federated Multi-Armed Bandits Under Byzantine Attacks

Multi-armed bandits (MAB) is a simple reinforcement learning model where...
βˆ™ 10/24/2020

Federated Bandit: A Gossiping Approach

In this paper, we study Federated Bandit, a decentralized Multi-Armed Ba...
βˆ™ 10/27/2022

Lifelong Bandit Optimization: No Prior and No Regret

In practical applications, machine learning algorithms are often repeate...