Differential privacy in policy optimization adds sample complexity costs that often appear as lower-order terms rather than dominating the bounds.
The cost of privacy: Optimal rates of convergence for parameter estimation with differential privacy.The Annals of Statistics, 49(5):2825–2850
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Introduces ePTR pipeline using safety lower bound testing to enable optimal DP mechanisms for sensitive estimators in classification and regression.
citing papers explorer
-
On the Sample Complexity of Differentially Private Policy Optimization
Differential privacy in policy optimization adds sample complexity costs that often appear as lower-order terms rather than dominating the bounds.
-
Efficient Propose-Test-Release for Optimal Differentially Private Estimation
Introduces ePTR pipeline using safety lower bound testing to enable optimal DP mechanisms for sensitive estimators in classification and regression.