# Federated X-Armed Bandit

arXiv: https://arxiv.org/abs/2205.15268 · HTML: https://mlsanity.com/paper/2205.15268/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 30 May 2022.

## Builds on (most cited first, 22 of 22)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [On Kernelized Multi-armed Bandits](https://mlsanity.com/paper/1704.00445/) (2017)
- [Batched Large-scale Bayesian Optimization in High-dimensional Spaces](https://mlsanity.com/paper/1706.01445/) (2017)
- [Differentially-Private Federated Linear Bandits](https://mlsanity.com/paper/2010.11425/) (2020)
- [Differentially Private Contextual Linear Bandits](https://mlsanity.com/paper/1810.00068/) (2018)
- [Federated Bayesian Optimization via Thompson Sampling](https://mlsanity.com/paper/2010.10154/) (2020)
- [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)
- [Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing](https://mlsanity.com/paper/2106.04502/) (2021)
- [Federated Bandit: A Gossiping Approach](https://mlsanity.com/paper/2010.12763/) (2020)
- [Algorithms for Differentially Private Multi-Armed Bandits](https://mlsanity.com/paper/1511.08681/) (2015)
- [Differentially Private Federated Bayesian Optimization with Distributed Exploration](https://mlsanity.com/paper/2110.14153/) (2021)
- [Federated Recommendation System via Differential Privacy](https://mlsanity.com/paper/2005.06670/) (2020)
- [A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption](https://mlsanity.com/paper/1810.00997/) (2018)
- [Lipschitz Bandits with Batched Feedback](https://mlsanity.com/paper/2110.09722/) (2021)
- [Federated Neural Bandits](https://mlsanity.com/paper/2205.14309/) (2022)
- [Online Stochastic Optimization under Correlated Bandit Feedback](https://mlsanity.com/paper/1402.0562/) (2014)
- [A Primal-dual Learning Algorithm for Personalized Dynamic Pricing with an Inventory Constraint](https://mlsanity.com/paper/1812.09234/) (2018)
- [Optimum-statistical Collaboration Towards General and Efficient Black-box Optimization](https://mlsanity.com/paper/2106.09215/) (2021)
- [Federated Online Sparse Decision Making](https://mlsanity.com/paper/2202.13448/) (2022)

## Built on by (most cited first, 5 of 5)

- [Federated Linear Contextual Bandits with User-level Differential Privacy](https://mlsanity.com/paper/2306.05275/) (2023)
- [PyXAB -- A Python Library for X-Armed Bandit and Online Blackbox Optimization Algorithms](https://mlsanity.com/paper/2303.04030/) (2023)
- [Federated Linear Dueling Bandits](https://mlsanity.com/paper/2502.01085/) (2025)
- [Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups](https://mlsanity.com/paper/2409.19092/) (2024)
- [Instance-dependent Stochastic Lipschitz bandit](https://mlsanity.com/paper/2605.29748/) (2026)

## Abstract (arXiv)

This work establishes the first framework of federated X-armed bandit, where different clients face heterogeneous local objective functions defined on the same domain and are required to collaboratively figure out the global optimum. We propose the first federated algorithm for such problems, named textttFed-PNE. By utilizing the topological structure of the global objective inside the hierarchical partitioning and the weak smoothness property, our algorithm achieves sublinear cumulative regret with respect to both the number of clients and the evaluation budget. Meanwhile, it only requires logarithmic communications between the central server and clients, protecting the client privacy. Experimental results on synthetic functions and real datasets validate the advantages of textttFed-PNE over various centralized and federated baseline algorithms.