mlsanityData to 14 Oct 2026

Privacy Amplification via Shuffling for Linear Contextual Bandits

arXiv 2112.06008 ↗First posted 11 Dec 2021cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

Contextual bandit algorithms are widely used in domains where it is desirable to provide a personalized service by leveraging contextual information, that may contain sensitive information that needs to be protected. Inspired by this scenario, we study the contextual linear bandit problem with differential privacy (DP) constraints. While the literature has focused on either centralized (joint DP) or local (local DP) privacy, we consider the shuffle model of privacy and we show that is possible to achieve a privacy/utility trade-off between JDP and LDP. By leveraging shuffling from privacy and batching from bandits, we present an algorithm with regret bound widetildeO(T2/3/varepsilon1/3), while guaranteeing both central (joint) and local privacy. Our result shows that it is possible to obtain a trade-off between JDP and LDP by leveraging the shuffle model while preserving local privacy.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 20 of its 31 references that are in the map. First posted on arXiv 11 Dec 2021.

Builds on

20 of 31 references.

References · 20

  1. 2016Deep Learning with Differential Privacycited by 2,728
  2. 2014RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Responsecited by 272
  3. 2018Amplification by Shuffling: From Local to Central Differential Privacy via Anonymitycited by 164
  4. 2018Distributed Differential Privacy via Shufflingcited by 115
  5. 2020Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shufflingcited by 96
  6. 2018Differentially Private Contextual Linear Banditscited by 82
  7. 2019The Privacy Blanket of the Shuffle Modelcited by 74
  8. 2020Sequential Batch Learning in Finite-Action Linear Contextual Banditscited by 63
  9. 2020Locally Differentially Private (Contextual) Bandits Learningcited by 53
  10. 2017Prochlo: Strong Privacy for Analytics in the Crowdcited by 51
  11. 2020Private Reinforcement Learning with PAC and Regret Guaranteescited by 51
  12. 2020Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluationcited by 39
8 more
  1. 2020Multi-Armed Bandits with Local Differential Privacycited by 37
  2. 2019Differential Privacy for Multi-armed Bandits: What Is It and What Is Its Cost?cited by 27
  3. 2021Differentially Private Multi-Armed Bandits in the Shuffle Modelcited by 24
  4. 2020The Elliptical Potential Lemma Revisitedcited by 23
  5. 2020Real-world Video Adaptation with Reinforcement Learningcited by 12
  6. 2020On Distributed Differential Privacy and Counting Distinct Elementscited by 8
  7. 2021Robo-Advising: Enhancing Investment with Inverse Optimization and Deep Reinforcement Learningcited by 7
  8. 2019Utility/Privacy Trade-off through the lens of Optimal Transportcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 5; 2024: 3; 2025: 3; 2026: 1.

17 papers.

Sort:

By area:

  1. 2022Shuffle Private Linear Contextual Banditscited by 27
  2. 2022Differentially Private Stochastic Linear Bandits: (Almost) for Freecited by 19
  3. 2022Near-Optimal Differentially Private Reinforcement Learningcited by 16
  4. 2022Distributed Differential Privacy in Multi-Armed Banditscited by 14
  5. 2023On Differentially Private Federated Linear Contextual Banditscited by 14
  6. 2023Federated Linear Contextual Bandits with User-level Differential Privacycited by 12
  7. 2022Differentially Private Linear Bandits with Partial Distributed Feedbackcited by 8
  8. 2023adaPARL: Adaptive Privacy-Aware Reinforcement Learning for Sequential-Decision Making Human-in-the-Loop Systemscited by 6
  9. 2025Differentially Private Kernelized Contextual Banditscited by 3
  10. 2023Concurrent Shuffle Differential Privacy Under Continual Observationcited by 2
  11. 2024FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Banditscited by 1
  12. 2024Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-upscited by 1
5 more
  1. 2024Near-Optimal Reinforcement Learning with Shuffle Differential Privacycited by 1
  2. 2026Shuffle and Joint Differential Privacy for Generalized Linear Contextual Banditscited by 1
  3. 2023Robust and differentially private stochastic linear banditscited by 0
  4. 2025Locally Private Nonparametric Contextual Multi-armed Banditscited by 0
  5. 2025Optimal Regret of Bernoulli Bandits under Global Differential Privacycited by 0