# Encrypted Linear Contextual Bandit

arXiv: https://arxiv.org/abs/2103.09927 · HTML: https://mlsanity.com/paper/2103.09927/

## Key facts

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

## Builds on (most cited first, 14 of 14)

- [A Survey on Homomorphic Encryption Schemes: Theory and Implementation](https://mlsanity.com/paper/1704.03578/) (2017)
- [Differentially Private Contextual Linear Bandits](https://mlsanity.com/paper/1810.00068/) (2018)
- [Provably Efficient Q-Learning with Low Switching Cost](https://mlsanity.com/paper/1905.12849/) (2019)
- [Sequential Batch Learning in Finite-Action Linear Contextual Bandits](https://mlsanity.com/paper/2004.06321/) (2020)
- [Federated Bandit: A Gossiping Approach](https://mlsanity.com/paper/2010.12763/) (2020)
- [Locally Differentially Private (Contextual) Bandits Learning](https://mlsanity.com/paper/2006.00701/) (2020)
- [Linear Bandits with Limited Adaptivity and Learning Distributional Optimal Design](https://mlsanity.com/paper/2007.01980/) (2020)
- [Algorithms for Differentially Private Multi-Armed Bandits](https://mlsanity.com/paper/1511.08681/) (2015)
- [Manipulation Attacks in Local Differential Privacy](https://mlsanity.com/paper/1909.09630/) (2019)
- [Contextual Multi-Armed Bandits for Causal Marketing](https://mlsanity.com/paper/1810.01859/) (2018)
- [Near-linear Time Gaussian Process Optimization with Adaptive Batching and Resparsification](https://mlsanity.com/paper/2002.09954/) (2020)
- [Towards the AlexNet Moment for Homomorphic Encryption: HCNN, theFirst Homomorphic CNN on Encrypted Data with GPUs](https://mlsanity.com/paper/1811.00778/) (2018)
- [Multinomial Logit Bandit with Low Switching Cost](https://mlsanity.com/paper/2007.04876/) (2020)
- [Encrypted accelerated least squares regression](https://mlsanity.com/paper/1703.00839/) (2017)

## 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.