New algorithm achieves optimal sampling of unbounded Gaussians under differential privacy constraints, suggesting a significant breakthrough.
We provide the first O(d)-sample algorithm for sampling from unbounded Gaussian distributions under the constraint of (ε, δ)-differential privacy. This is a quadratic improvement over previous results for the same problem, settling an open question of Ghazi, Hu, Kumar, and Manurangsi.
No takes yet. Share an insight, caveat, or question.
Iverson et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: