no code implementations • 9 Jun 2023 • Hua Wang, Sheng Gao, Huanyu Zhang, Weijie J. Su, Milan Shen
In our paper, we introduce DP-HyPO, a pioneering framework for ``adaptive'' private hyperparameter optimization, aiming to bridge the gap between private and non-private hyperparameter optimization.
no code implementations • 8 Jun 2023 • Ruiquan Huang, Huanyu Zhang, Luca Melis, Milan Shen, Meisam Hajzinia, Jing Yang
This paper studies federated linear contextual bandits under the notion of user-level differential privacy (DP).
1 code implementation • 9 Jun 2022 • Hua Wang, Sheng Gao, Huanyu Zhang, Milan Shen, Weijie J. Su
Many modern machine learning algorithms are composed of simple private algorithms; thus, an increasingly important problem is to efficiently compute the overall privacy loss under composition.