Proposes Wasserstein Projection Mechanism for differentially private sampling that optimizes Wasserstein distance utility and provides convergence guarantees for approximate computation.
Learning with differentially private (sliced) wasserstein gradients.arXiv preprint arXiv:2502.01701
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Proves graphical convergence of empirical subdifferentials for sampled OT objectives to the population subdifferential, ensuring subgradient methods approach stationary points of the true problem.
citing papers explorer
-
Differentially Private Sampling from Distributions via Wasserstein Projection
Proposes Wasserstein Projection Mechanism for differentially private sampling that optimizes Wasserstein distance utility and provides convergence guarantees for approximate computation.
-
Convergence of empirical subgradients for optimal transport-based objectives
Proves graphical convergence of empirical subdifferentials for sampled OT objectives to the population subdifferential, ensuring subgradient methods approach stationary points of the true problem.