collaborators

7 papers

cs.DS2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.CC2026

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…

cs.CR2026

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…

cs.CR2025

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…