Differentially Private Sampling from Distributions via Wasserstein Projection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Takakura, Shokichi, Liew, Seng Pei, Hasegawa, Satoshi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918494015062016
author Takakura, Shokichi
Liew, Seng Pei
Hasegawa, Satoshi
author_facet Takakura, Shokichi
Liew, Seng Pei
Hasegawa, Satoshi
contents In this paper, we study the problem of sampling from a distribution under the constraint of differential privacy (DP). Prior works measure the utility of DP sampling with density ratio-based measures such as KL divergence. However, such formulations suffer from two key limitations: 1) they fail to capture the geometric structure of the support, and 2) they are not applicable when the supports of the distributions differ. To deal with these issues, we develop a novel framework for DP sampling with Wasserstein distance as the utility measure. In this formulation, we propose Wasserstein Projection Mechanism (WPM), a minimax optimal mechanism based on Wasserstein projection. Furthermore, we develop efficient algorithms for computing the proposed mechanisms approximately and provide convergence guarantees.
format Preprint
id arxiv_https___arxiv_org_abs_2605_10015
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Differentially Private Sampling from Distributions via Wasserstein Projection
Takakura, Shokichi
Liew, Seng Pei
Hasegawa, Satoshi
Machine Learning
Cryptography and Security
In this paper, we study the problem of sampling from a distribution under the constraint of differential privacy (DP). Prior works measure the utility of DP sampling with density ratio-based measures such as KL divergence. However, such formulations suffer from two key limitations: 1) they fail to capture the geometric structure of the support, and 2) they are not applicable when the supports of the distributions differ. To deal with these issues, we develop a novel framework for DP sampling with Wasserstein distance as the utility measure. In this formulation, we propose Wasserstein Projection Mechanism (WPM), a minimax optimal mechanism based on Wasserstein projection. Furthermore, we develop efficient algorithms for computing the proposed mechanisms approximately and provide convergence guarantees.
title Differentially Private Sampling from Distributions via Wasserstein Projection
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2605.10015