differentially private
A property of algorithms that ensures the privacy of individual data points while still allowing for aggregate insights, often leveraging techniques like noise injection to protect sensitive information.
- On the Sample Complexity of Differentially Private Policy Optimization
- Private Evolution Converges
- Private Statistical Estimation via Truncation
- Second-Order Convergence in Private Stochastic Non-Convex Optimization
- Spectral Perturbation Bounds for Low-Rank Approximation with Applications to Privacy
- Spectral Perturbation Bounds for Low-Rank Approximation with Applications to Privacy