mlsanityData to 14 Oct 2026

Federated Linear Contextual Bandits with User-level Differential Privacy

arXiv 2306.05275 ↗First posted 8 Jun 2023cs.LG cs.CR cs.ITcited by 12

Not on the map. Why?

Abstract (arXiv)

This paper studies federated linear contextual bandits under the notion of user-level differential privacy (DP). We first introduce a unified federated bandits framework that can accommodate various definitions of DP in the sequential decision-making setting. We then formally introduce user-level central DP (CDP) and local DP (LDP) in the federated bandits framework, and investigate the fundamental trade-offs between the learning regrets and the corresponding DP guarantees in a federated linear contextual bandits model. For CDP, we propose a federated algorithm termed as textttROBIN and show that it is near-optimal in terms of the number of clients M and the privacy budget varepsilon by deriving nearly-matching upper and lower regret bounds when user-level DP is satisfied. For LDP, we obtain several lower bounds, indicating that learning under user-level (varepsilon,δ)-LDP must suffer a regret blow-up factor at least min1/varepsilon,M or min1/√varepsilon,√M under different conditions.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 44 of its 78 references that are in the map. First posted on arXiv 8 Jun 2023.

Builds on

44 of 78 references.

References · 44

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 246
  3. 2018Privately Learning High-Dimensional Distributionscited by 104
  4. 2020Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shufflingcited by 96
  5. 2020Differentially-Private Federated Linear Banditscited by 83
  6. 2018Differentially Private Contextual Linear Banditscited by 82
  7. 2021Learning with User-Level Privacycited by 72
  8. 2021Federated Multi-armed Bandits with Personalizationcited by 62
  9. 2021Federated Linear Contextual Banditscited by 61
  10. 2021Federated Multi-Armed Banditscited by 59
  11. 2020Differentially Private Assouad, Fano, and Le Camcited by 55
  12. 2020Federated Bandit: A Gossiping Approachcited by 55
32 more
  1. 2020Locally Differentially Private (Contextual) Bandits Learningcited by 53
  2. 2015Algorithms for Differentially Private Multi-Armed Banditscited by 45
  3. 2019Adaptive Exploration in Linear Contextual Banditcited by 43
  4. 2020Learning discrete distributions: user vs item-level privacycited by 41
  5. 2019An Optimal Private Stochastic-MAB Algorithm Based on an Optimal Private Stopping Rulecited by 37
  6. 2020Multi-Armed Bandits with Local Differential Privacycited by 37
  7. 2021Asynchronous Upper Confidence Bound Algorithms for Federated Linear Banditscited by 31
  8. 2021Leveraging Good Representations in Linear Contextual Banditscited by 29
  9. 2021Generalized Linear Bandits with Local Differential Privacycited by 29
  10. 2022A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Banditscited by 28
  11. 2022When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Banditscited by 28
  12. 2022Shuffle Private Linear Contextual Banditscited by 27
  13. 2016Make Up Your Mind: The Price of Online Queries in Differential Privacycited by 26
  14. 2017Generalization for Adaptively-chosen Estimators via Stable Mediancited by 26
  15. 2020Federated Recommendation System via Differential Privacycited by 26
  16. 2021Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Banditscited by 25
  17. 2021Differentially Private Multi-Armed Bandits in the Shuffle Modelcited by 24
  18. 2020The Elliptical Potential Lemma Revisitedcited by 23
  19. 2022Differentially Private Stochastic Linear Bandits: (Almost) for Freecited by 19
  20. 2021Local Differential Privacy Is Equivalent to Contraction of Eγ-Divergencecited by 17
  21. 2021Privacy Amplification via Shuffling for Linear Contextual Banditscited by 17
  22. 2022Discrete Distribution Estimation under User-level Local Differential Privacycited by 17
  23. 2018The K-Nearest Neighbour UCB algorithm for multi-armed bandits with covariatescited by 16
  24. 2020(Locally) Differentially Private Combinatorial Semi-Banditscited by 14
  25. 2022Distributed Differential Privacy in Multi-Armed Banditscited by 14
  26. 2023On Differentially Private Federated Linear Contextual Banditscited by 14
  27. 2022Communication Efficient Federated Learning for Generalized Linear Banditscited by 13
  28. 2022Private and Byzantine-Proof Cooperative Decision-Makingcited by 10
  29. 2022Differentially Private Linear Bandits with Partial Distributed Feedbackcited by 8
  30. 2022Federated X-Armed Banditcited by 5
  31. 2022Dynamic Global Sensitivity for Differentially Private Contextual Banditscited by 5
  32. 2022Federated Online Sparse Decision Makingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 5; 2025: 4; 2026: 1.

12 papers.

  1. 2024Fine-Tuning Large Language Models with User-Level Differential Privacycited by 29
  2. 2024A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacycited by 11
  3. 2023Pure Exploration in Asynchronous Federated Banditscited by 6
  4. 2024Exactly Minimax-Optimal Locally Differentially Private Samplingcited by 5
  5. 2024Learning with User-Level Local Differential Privacycited by 3
  6. 2025Differentially Private Kernelized Contextual Banditscited by 3
  7. 2025Locally Optimal Private Sampling: Beyond the Global Minimaxcited by 2
  8. 2023Harnessing the Power of Federated Learning in Federated Contextual Banditscited by 1
  9. 2024Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-upscited by 1
  10. 2025Locally Private Nonparametric Contextual Multi-armed Banditscited by 0
  11. 2025Differential Privacy in Kernelized Contextual Bandits via Random Projectionscited by 0
  12. 2026Matrix Factorization for Practical Continual Mean Estimation Under User-Level Differential Privacycited by 0