SAMBA: A Generic Framework for Secure Federated Multi-Armed Bandits

DOI10.1613/JAIR.1.13163MaRDI QIDQ5076321zbMATH OpenOpenAlexFDO

Authors Radu Ciucanu, Pascal Lafourcade, Gael Marcadet, Marta Soare

Publication date 16 May 2022

Published in Journal of Artificial Intelligence Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1613/jair.1.13163

zbMATH Keywords

machine learningreinforcement learningdistributed AI

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Recommendations

• Secure cumulative reward maximization in linear stochastic bandits
• Secure best arm identification in multi-armed bandits
• Corrupt bandits for preserving local privacy
• Differentially private and budget-limited bandit learning over matroids
• Game of thrones: fully distributed learning for multiplayer bandits

Cites work

• A Tutorial on Thompson Sampling
• Advances and Open Problems in Federated Learning
• Efficient homomorphic comparison methods with optimal complexity
• Eigentaste: A constant time collaborative filtering algorithm
• Foundations of Cryptography
• Fully homomorphic encryption using ideal lattices
• Public-Key Cryptosystems Based on Composite Degree Residuosity Classes
• Reinforcement learning. An introduction
• Secure best arm identification in multi-armed bandits
• Secure cumulative reward maximization in linear stochastic bandits
• The algorithmic foundations of differential privacy

Cited in

(1)

• SAMBA

Describes a project that uses

Uses Software

• MovieLens

This page was built for publication: SAMBA: A Generic Framework for Secure Federated Multi-Armed Bandits

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5076321)