Differentially Private Federated Bayesian Optimization with Distributed Exploration
Dez 6, 2021
Sprecher:innen
Zhongxiang Dai
Řečník · 0 sledujících
Bryan Kian
Řečník · 2 sledující
Patrick Jaillet
Řečník · 0 sledujících
Über
Bayesian optimization (BO) has recently been extended to the federated learning (FL) setting by the federated Thompson sampling (FTS) algorithm. 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 practical trade-off between privacy and utility.Bayesian optimization (BO) has recently been extended to the federated learning (FL) setting by the federated Thompson sampling (FTS) algorithm. 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 preser…
Organisator
NeurIPS 2021
Účet · 1,9k sledujících
Über NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Gefällt euch das Format? Vertraut auf SlidesLive, um euer nächstes Event festzuhalten!
Professionelle Aufzeichnung und Livestreaming – weltweit.
Freigeben
Empfohlene Videos
Präsentationen, deren Thema, Kategorie oder Sprecher:in ähnlich sind
Effect of Model Size on Worst-group Generalization
Zhlédnout později
Alan Pham, …
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Zoom Q&A for Contributed talks Session 1+2
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
ResT: An Efficient Transformer for Visual Recognition
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
On sensitivity of meta-learning to support data
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Modeling Worlds in Text
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
The State Capture Recommender System: An Unsupervised Machine Learning Approach to Topic Modelling
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %