41 citations · 166 across the 36 of their papers we have counts for
47 papers
Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?
Andy Dong, Ayfer Özgür
Poisson subsampling is the default sampling scheme in differentially private machine learning, largely because its unstructured randomness yields tractable privacy amplification an…
The Performance of Compression-Based Denoisers
Dan Song, Ayfer Özgür, Tsachy Weissman
We consider a denoiser that reconstructs a stationary ergodic source by lossily compressing samples of the source observed through a memoryless noisy channel. Prior work on compres…
Information Compression in the AI Era: Recent Advances and Future Challenges
Jun Chen, Yong Fang, Ashish Khisti +3
This survey articles focuses on emerging connections between the fields of machine learning and data compression. While fundamental limits of classical (lossy) data compression are…
Universal Exact Compression of Differentially Private Mechanisms
Yanxiao Liu, Wei-Ning Chen, Ayfer Özgür +1
To reduce the communication cost of differential privacy mechanisms, we introduce a novel construction, called Poisson private representation (PPR), designed to compress and simula…
Federated Experiment Design under Distributed Differential Privacy
Wei-Ning Chen, Graham Cormode, Akash Bharadwaj +2
Experiment design has a rich history dating back over a century and has found many critical applications across various fields since then. The use and collection of users' data in…
Training generative models from privatized data
Daria Reshetova, Wei-Ning Chen, Ayfer Özgür
Local differential privacy is a powerful method for privacy-preserving data collection. In this paper, we develop a framework for training Generative Adversarial Networks (GANs) on…