Proposes Wasserstein Projection Mechanism for differentially private sampling that optimizes Wasserstein distance utility and provides convergence guarantees for approximate computation.
Then f( ¯mT )−f(m ∗)≤ βDp α r 2(1 + logk) T =O β α Dp r logk T !
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.