72 citations · 394 across the 35 of their papers we have counts for
8 papers · 1 filter
Public Data-Assisted Mirror Descent for Private Model Training
Ehsan Amid, Arun Ganesh, Rajiv Mathews +6
In this paper, we revisit the problem of using in-distribution public data to improve the privacy/utility trade-offs for differentially private (DP) model training. (Here, public d…
A Private and Computationally-Efficient Estimator for Unbounded Gaussians
Gautam Kamath, Argyris Mouzakis, Vikrant Singhal +2
We give the first polynomial-time, polynomial-sample, differentially private estimator for the mean and covariance of an arbitrary Gaussian distribution in $\mat…
Hyperparameter Tuning with Renyi Differential Privacy
Nicolas Papernot, Thomas Steinke
For many differentially private algorithms, such as the prominent noisy stochastic gradient descent (DP-SGD), the analysis needed to bound the privacy leakage of a single training…
PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes
Peter Grünwald, Thomas Steinke, Lydia Zakynthinou
We give a novel, unified derivation of conditional PAC-Bayesian and mutual information (MI) generalization bounds. We derive conditional MI bounds as an instance, with special choi…
The Permute-and-Flip Mechanism is Identical to Report-Noisy-Max with Exponential Noise
Zeyu Ding, Daniel Kifer, Sayed M. Saghaian N. E. +4
The permute-and-flip mechanism is a recently proposed differentially private selection algorithm that was shown to outperform the exponential mechanism. In this paper, we show that…
Privately Learning Subspaces
Vikrant Singhal, Thomas Steinke
Private data analysis suffers a costly curse of dimensionality. However, the data often has an underlying low-dimensional structure. For example, when optimizing via gradient desce…
Leveraging Public Data for Practical Private Query Release
Terrance Liu, Giuseppe Vietri, Thomas Steinke +2
In many statistical problems, incorporating priors can significantly improve performance. However, the use of prior knowledge in differentially private query release has remained u…
The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation
Peter Kairouz, Ziyu Liu, Thomas Steinke
We consider training models on private data that are distributed across user devices. To ensure privacy, we add on-device noise and use secure aggregation so that only the noisy su…