7 papers
Edit-Neighboring Data Streams and Privacy under Continual Observation
Joel Daniel Andersson, Anamay Chaturvedi, Monika Henzinger +1
Differential privacy under Continual Observation (CO) quantifies the loss in privacy that occurs when outputs generated using a stream of sensitive input data are published in the…
Beyond Square Roots: Explicit Memory-Efficient Factorization for Multi-Epoch Private Learning
Nikita P. Kalinin, Aki Rehn, Joel Daniel Andersson +2
Correlated-noise mechanisms are among the most promising approaches for improving the utility of differentially private model training, but rigorous guarantees require explicit, an…
Learning Rate Scheduling with Matrix Factorization for Private Training
Nikita P. Kalinin, Joel Daniel Andersson
We study differentially private model training with stochastic gradient descent under learning rate scheduling and correlated noise. Although correlated noise, in particular via ma…
On the Space Complexity of Online Convolution
Joel Daniel Andersson, Amir Yehudayoff
We study a discrete convolution streaming problem. An input arrives as a stream of numbers , and at time our goal is to output where is a…
Improved Accuracy for Private Continual Cardinality Estimation in Fully Dynamic Streams via Matrix Factorization
Joel Daniel Andersson, Palak Jain, Satchit Sivakumar
We study differentially-private statistics in the fully dynamic continual observation model, where many updates can arrive at each time step and updates to a stream can involve bot…
Private Lossless Multiple Release
Joel Daniel Andersson, Lukas Retschmeier, Boel Nelson +1
Koufogiannis et al. (2016) showed a result for Laplace noise-based differentially private mechanisms: given an -DP release, a new release wi…