# Federated Linear Contextual Bandits with User-level Differential Privacy

arXiv: https://arxiv.org/abs/2306.05275 · HTML: https://mlsanity.com/paper/2306.05275/

## 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 (most cited first, 30 of 44)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning](https://mlsanity.com/paper/1812.00535/) (2018)
- [Privately Learning High-Dimensional Distributions](https://mlsanity.com/paper/1805.00216/) (2018)
- [Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling](https://mlsanity.com/paper/2012.12803/) (2020)
- [Differentially-Private Federated Linear Bandits](https://mlsanity.com/paper/2010.11425/) (2020)
- [Differentially Private Contextual Linear Bandits](https://mlsanity.com/paper/1810.00068/) (2018)
- [Learning with User-Level Privacy](https://mlsanity.com/paper/2102.11845/) (2021)
- [Federated Multi-armed Bandits with Personalization](https://mlsanity.com/paper/2102.13101/) (2021)
- [Federated Linear Contextual Bandits](https://mlsanity.com/paper/2110.14177/) (2021)
- [Federated Multi-Armed Bandits](https://mlsanity.com/paper/2101.12204/) (2021)
- [Differentially Private Assouad, Fano, and Le Cam](https://mlsanity.com/paper/2004.06830/) (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)
- [Algorithms for Differentially Private Multi-Armed Bandits](https://mlsanity.com/paper/1511.08681/) (2015)
- [Adaptive Exploration in Linear Contextual Bandit](https://mlsanity.com/paper/1910.06996/) (2019)
- [Learning discrete distributions: user vs item-level privacy](https://mlsanity.com/paper/2007.13660/) (2020)
- [An Optimal Private Stochastic-MAB Algorithm Based on an Optimal Private Stopping Rule](https://mlsanity.com/paper/1905.09383/) (2019)
- [Multi-Armed Bandits with Local Differential Privacy](https://mlsanity.com/paper/2007.03121/) (2020)
- [Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits](https://mlsanity.com/paper/2110.01463/) (2021)
- [Leveraging Good Representations in Linear Contextual Bandits](https://mlsanity.com/paper/2104.03781/) (2021)
- [Generalized Linear Bandits with Local Differential Privacy](https://mlsanity.com/paper/2106.03365/) (2021)
- [A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits](https://mlsanity.com/paper/2207.03106/) (2022)
- [When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits](https://mlsanity.com/paper/2209.02570/) (2022)
- [Shuffle Private Linear Contextual Bandits](https://mlsanity.com/paper/2202.05567/) (2022)
- [Make Up Your Mind: The Price of Online Queries in Differential Privacy](https://mlsanity.com/paper/1604.04618/) (2016)
- [Generalization for Adaptively-chosen Estimators via Stable Median](https://mlsanity.com/paper/1706.05069/) (2017)
- [Federated Recommendation System via Differential Privacy](https://mlsanity.com/paper/2005.06670/) (2020)
- [Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits](https://mlsanity.com/paper/2106.02575/) (2021)
- [Differentially Private Multi-Armed Bandits in the Shuffle Model](https://mlsanity.com/paper/2106.02900/) (2021)
- [The Elliptical Potential Lemma Revisited](https://mlsanity.com/paper/2010.10182/) (2020)

## Built on by (most cited first, 12 of 12)

- [Fine-Tuning Large Language Models with User-Level Differential Privacy](https://mlsanity.com/paper/2407.07737/) (2024)
- [A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy](https://mlsanity.com/paper/2405.13453/) (2024)
- [Pure Exploration in Asynchronous Federated Bandits](https://mlsanity.com/paper/2310.11015/) (2023)
- [Exactly Minimax-Optimal Locally Differentially Private Sampling](https://mlsanity.com/paper/2410.22699/) (2024)
- [Learning with User-Level Local Differential Privacy](https://mlsanity.com/paper/2405.17079/) (2024)
- [Differentially Private Kernelized Contextual Bandits](https://mlsanity.com/paper/2501.07046/) (2025)
- [Locally Optimal Private Sampling: Beyond the Global Minimax](https://mlsanity.com/paper/2510.09485/) (2025)
- [Harnessing the Power of Federated Learning in Federated Contextual Bandits](https://mlsanity.com/paper/2312.16341/) (2023)
- [Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups](https://mlsanity.com/paper/2409.19092/) (2024)
- [Locally Private Nonparametric Contextual Multi-armed Bandits](https://mlsanity.com/paper/2503.08098/) (2025)
- [Differential Privacy in Kernelized Contextual Bandits via Random Projections](https://mlsanity.com/paper/2507.13639/) (2025)
- [Matrix Factorization for Practical Continual Mean Estimation Under User-Level Differential Privacy](https://mlsanity.com/paper/2601.22320/) (2026)

## 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.