privacy budget
A limit on the amount of personal information that can be shared or processed under privacy-preserving frameworks, especially in federated learning and differential privacy contexts, aimed at safeguarding user data while enabling machine learning.
- Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy
- Multi-Class Support Vector Machine with Differential Privacy
- Online robust locally differentially private learning for nonparametric regression
- Optimal Regret of Bandits under Differential Privacy
- Private Hyperparameter Tuning with Ex-Post Guarantee
- Setting $\varepsilon$ is not the Issue in Differential Privacy