The following pages link to What Can We Learn Privately? (Q3093624):
Displaying 12 items.
- Topics and Techniques in Distribution Testing: A Biased but Representative Sample (Q5870774) (← links)
- An accurate, scalable and verifiable protocol for federated differentially private averaging (Q6097108) (← links)
- Distribution-invariant differential privacy (Q6108260) (← links)
- Adversarial manifold estimation (Q6118078) (← links)
- Community detection in decentralized social networks with local differential privacy (Q6126866) (← links)
- PAC learning halfspaces in non-interactive local differential privacy model with public unlabeled data (Q6141043) (← links)
- Privacy amplification for wireless federated learning with Rényi differential privacy and subsampling (Q6153177) (← links)
- Interactive versus noninteractive locally differentially private estimation: two elbows for the quadratic functional (Q6172183) (← links)
- A novel privacy-preserving graph convolutional network via secure matrix multiplication (Q6179965) (← links)
- Post-selection inference via algorithmic stability (Q6183754) (← links)
- Differentially private inference via noisy optimization (Q6183772) (← links)
- Differential privacy: getting more for less (Q6198644) (← links)