Timezone: »

 
Poster
Differentially Private Federated Bayesian Optimization with Distributed Exploration
Zhongxiang Dai · Bryan Kian Hsiang Low · Patrick Jaillet

Thu Dec 09 04:30 PM -- 06:00 PM (PST) @ Virtual
in Poster Session 7 »

Bayesian optimization (BO) has recently been extended to the federated learning (FL) setting by the federated Thompson sampling (FTS) algorithm, which has promising applications such as federated hyperparameter tuning. However, FTS is not equipped with a rigorous privacy guarantee which is an important consideration in FL. Recent works have incorporated differential privacy (DP) into the training of deep neural networks through a general framework for adding DP to iterative algorithms. Following this general DP framework, our work here integrates DP into FTS to preserve user-level privacy. We also leverage the ability of this general DP framework to handle different parameter vectors, as well as the technique of local modeling for BO, to further improve the utility of our algorithm through distributed exploration (DE). The resulting differentially private FTS with DE (DP-FTS-DE) algorithm is endowed with theoretical guarantees for both the privacy and utility and is amenable to interesting theoretical insights about the privacy-utility trade-off. We also use real-world experiments to show that DP-FTS-DE achieves high utility (competitive performance) with a strong privacy guarantee (small privacy loss) and induces a trade-off between privacy and utility.

Keywords: Deep Learning · Optimization · Reinforcement Learning and Planning · Privacy · Federated Learning

Author Information

Zhongxiang Dai (National University of Singapore)
Bryan Kian Hsiang Low (National University of Singapore)
Patrick Jaillet (MIT)

More from the Same Authors