Name
Abstract | ||
|---|---|---|
In this paper, we study the problem of global reward maximization with only partial distributed feedback. This problem is motivated by several real-world applications (e.g., cellular network configuration, dynamic pricing, and policy selection) where an action taken by a central entity influences a large population that contributes to the global reward. However, collecting such reward feedback from the entire population not only incurs a prohibitively high cost, but often leads to privacy concerns. To tackle this problem, we consider differentially private distributed linear bandits, where only a subset of users from the population are selected (called clients) to participate in the learning process and the central server learns the global model from such partial feedback by iteratively aggregating these clients’ local feedback in a differentially private fashion. We then propose a unified algorithmic learning framework, called differentially private distributed phased elimination (DP-DPE), which can be naturally integrated with popular differential privacy (DP) models (including central DP, local DP, and shuffle DP). Furthermore, we prove that DP-DPE achieves both sublinear regret and sublinear communication cost. Interestingly, DP-DPE also achieves privacy protection “for free” in the sense that the additional cost due to privacy guarantees is a lower-order additive term. Finally, we conduct simulations to corroborate our theoretical results and demonstrate the effectiveness of DP-DPE. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.23919/WiOpt56218.2022.9930524 | 2022 20th International Symposium on Modeling and Optimization in Mobile, Ad hoc, and Wireless Networks (WiOpt) |
Keywords | DocType | ISBN |
differentially private distributed linear bandits,called clients,learning process,central server,global model,partial feedback,differentially private fashion,unified algorithmic learning framework,called differentially private distributed phased elimination,DP-DPE,popular differential privacy models,including central DP,local DP,shuffle DP,private linear bandits,partial distributed feedback,global reward maximization,cellular network configuration,policy selection,central entity,reward feedback,entire population,prohibitively high cost,privacy concerns | Conference | 978-1-6654-6076-7 |
Citations | PageRank | References |
0 | 0.34 | 5 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Fengjiao Li | 1 | 0 | 0.34 |
| Xingyu Zhou | 2 | 0 | 0.34 |
| Bo Ji | 3 | 0 | 0.34 |