mlsanityData to 7 Oct 2026

Encrypted Linear Contextual Bandit

arXiv 2103.09927 ↗First posted 17 Mar 2021cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Contextual bandit is a general framework for online learning in sequential decision-making problems that has found application in a wide range of domains, including recommendation systems, online advertising, and clinical trials. A critical aspect of bandit methods is that they require to observe the contexts --i.e., individual or group-level data-- and rewards in order to solve the sequential problem. The large deployment in industrial applications has increased interest in methods that preserve the users' privacy. In this paper, we introduce a privacy-preserving bandit framework based on homomorphic encryptioncolorviolet which allows computations using encrypted data. The algorithm textitonly observes encrypted information (contexts and rewards) and has no ability to decrypt it. Leveraging the properties of homomorphic encryption, we show that despite the complexity of the setting, it is possible to solve linear contextual bandits over encrypted data with a widetildeO(d√T) regret bound in any linear contextual bandit problem, while keeping data encrypted.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 56 references that are in the map. First posted on arXiv 17 Mar 2021.

Builds on

14 of 56 references.

References · 14

  1. 2017A Survey on Homomorphic Encryption Schemes: Theory and Implementationcited by 154
  2. 2018Differentially Private Contextual Linear Banditscited by 82
  3. 2019Provably Efficient Q-Learning with Low Switching Costcited by 77
  4. 2020Sequential Batch Learning in Finite-Action Linear Contextual Banditscited by 63
  5. 2020Federated Bandit: A Gossiping Approachcited by 55
  6. 2020Locally Differentially Private (Contextual) Bandits Learningcited by 52
  7. 2020Linear Bandits with Limited Adaptivity and Learning Distributional Optimal Designcited by 51
  8. 2015Algorithms for Differentially Private Multi-Armed Banditscited by 44
  9. 2019Manipulation Attacks in Local Differential Privacycited by 23
  10. 2018Contextual Multi-Armed Bandits for Causal Marketingcited by 17
  11. 2020Near-linear Time Gaussian Process Optimization with Adaptive Batching and Resparsificationcited by 13
  12. 2018Towards the AlexNet Moment for Homomorphic Encryption: HCNN, theFirst Homomorphic CNN on Encrypted Data with GPUscited by 11
2 more
  1. 2020Multinomial Logit Bandit with Low Switching Costcited by 10
  2. 2017Encrypted accelerated least squares regressioncited by 2

Built on by

Not cited yet.