mlsanityData to 7 Oct 2026

Locally Private Nonparametric Contextual Multi-armed Bandits

arXiv 2503.08098 ↗First posted 11 Mar 2025stat.ML cs.LG stat.MEcited by 0

Not on the map. Why?

Abstract (arXiv)

Motivated by privacy concerns in sequential decision-making on sensitive data, we address the challenge of nonparametric contextual multi-armed bandits (MAB) under local differential privacy (LDP). We develop a uniform-confidence-bound-type estimator, showing its minimax optimality supported by a matching minimax lower bound. We further consider the case where auxiliary datasets are available, subject also to (possibly heterogeneous) LDP constraints. Under the widely-used covariate shift framework, we propose a jump-start scheme to effectively utilize the auxiliary data, the minimax optimality of which is further established by a matching lower bound. Comprehensive experiments on both synthetic and real-world datasets validate our theoretical results and underscore the effectiveness of the proposed methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 39 of its 61 references that are in the map. First posted on arXiv 11 Mar 2025.

Builds on

39 of 61 references.

References · 39

  1. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  2. 2013The Composition Theorem for Differential Privacycited by 290
  3. 2014RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Responsecited by 262
  4. 2016Minimax Optimal Procedures for Locally Private Estimationcited by 103
  5. 2020Transfer Learning for High-dimensional Linear Regression: Prediction, Estimation, and Minimax Optimalitycited by 89
  6. 2020Differentially-Private Federated Linear Banditscited by 83
  7. 2018Differentially Private Contextual Linear Banditscited by 82
  8. 2018Marginal Singularity, and the Benefits of Labels in Covariate-Shiftcited by 65
  9. 2019Transfer Learning for Nonparametric Classification: Minimax Rate and Adaptive Classifiercited by 64
  10. 2020Locally Differentially Private (Contextual) Bandits Learningcited by 52
  11. 2017Multi-Task Learning for Contextual Banditscited by 47
  12. 2014Rates of Convergence for Nearest Neighbor Classificationcited by 45
27 more
  1. 2017Privacy Loss in Apple's Implementation of Differential Privacy on MacOS 10.12cited by 42
  2. 2020Local Differential Privacy and Its Applications: A Comprehensive Surveycited by 40
  3. 2022A new similarity measure for covariate shift with applications to nonparametric regressioncited by 33
  4. 2018Balanced Linear Contextual Banditscited by 30
  5. 2021Generalized Linear Bandits with Local Differential Privacycited by 29
  6. 2022Shuffle Private Linear Contextual Banditscited by 27
  7. 2022Transfer Learning for Contextual Multi-armed Banditscited by 24
  8. 2024Transfer Learning for Nonparametric Regression: Non-asymptotic Minimax Analysis and Adaptive Procedurecited by 19
  9. 2021Privacy Amplification via Shuffling for Linear Contextual Banditscited by 17
  10. 2020Multitask Bandit Learning Through Heterogeneous Feedback Aggregationcited by 14
  11. 2020Offline Contextual Multi-armed Bandits for Mobile Health Interventions: A Case Study on Emotion Regulationcited by 13
  12. 2021Differential Privacy in Personalized Pricing with Nonparametric Demand Modelscited by 13
  13. 2015Differentially Private Bayesian Optimizationcited by 12
  14. 2020Self-Tuning Bandits over Unknown Covariate-Shiftscited by 12
  15. 2023Federated Linear Contextual Bandits with User-level Differential Privacycited by 12
  16. 2023Simple Binary Hypothesis Testing under Local Differential Privacy and Communication Constraintscited by 10
  17. 2019Classification under local differential privacycited by 9
  18. 2020Strongly universally consistent nonparametric regression and classification with privatised datacited by 8
  19. 2020Hedging using reinforcement learning: Contextual k-Armed Bandit versus Q-learningcited by 7
  20. 2023Optimal Locally Private Nonparametric Classification with Public Datacited by 7
  21. 2022Dynamic Global Sensitivity for Differentially Private Contextual Banditscited by 5
  22. 2021Locally private online change point detectioncited by 3
  23. 2024Locally Private Estimation with Public Featurescited by 3
  24. 2024Contextual Dynamic Pricing: Algorithms, Optimality, and Local Differential Privacy Constraintscited by 3
  25. 2024On the Optimal Regret of Locally Private Linear Contextual Banditcited by 2
  26. 2025Beyond Covariance Matrix: The Statistical Complexity of Private Linear Regressioncited by 2
  27. 2024FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Banditscited by 1

Built on by

Not cited yet.