Related papers: Differentially Private Wasserstein Barycenters

Differentially Private Wasserstein Barycenters

URL: http://arxiv.org/abs/2510.03021v1
Date: Fri, 03 Oct 2025 14:02:46 GMT
Title: Differentially Private Wasserstein Barycenters
Authors: Anming Gu, Sasidhar Kunapuli, Mark Bun, Edward Chien, Kristjan Greenewald,
Abstract summary: We present the first algorithms for computing Wasserstein barycenters under differential privacy.<n>Our methods produce high-quality private barycenters with strong accuracy-privacy tradeoffs.
Score: 9.025699764473819
License: http://creativecommons.org/licenses/by/4.0/
Abstract: The Wasserstein barycenter is defined as the mean of a set of probability measures under the optimal transport metric, and has numerous applications spanning machine learning, statistics, and computer graphics. In practice these input measures are empirical distributions built from sensitive datasets, motivating a differentially private (DP) treatment. We present, to our knowledge, the first algorithms for computing Wasserstein barycenters under differential privacy. Empirically, on synthetic data, MNIST, and large-scale U.S. population datasets, our methods produce high-quality private barycenters with strong accuracy-privacy tradeoffs.

Related papers

Linear-Time User-Level DP-SCO via Robust Statistics [55.350093142673316]
User-level differentially private convex optimization (DP-SCO) has garnered significant attention due to the importance of safeguarding user privacy in machine learning applications.<n>Current methods, such as those based on differentially private gradient descent (DP-SGD), often struggle with high noise accumulation and suboptimal utility.<n>We introduce a novel linear-time algorithm that leverages robust statistics, specifically the median and trimmed mean, to overcome these challenges.
arXiv Detail & Related papers (2025-02-13T02:05:45Z)
Differentially Private Random Feature Model [47.35176457481132]
We produce a differentially private random feature model for privacy-preserving kernel machines.<n>We show that our method preserves privacy and derive a generalization error bound for the method.
arXiv Detail & Related papers (2024-12-06T05:31:08Z)
Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal Transport [84.51977664336056]
We propose a novel scalable approach for estimating the robust continuous barycenter.<n>Our method is framed as a min-max optimization problem and is adaptable to general cost functions.
arXiv Detail & Related papers (2024-10-04T23:27:33Z)
Private Wasserstein Distance [6.015898117103069]
Wasserstein distance is a key metric for quantifying data divergence from a distributional perspective.<n>In this study, we explore the inherent triangular properties within the Wasserstein space, leading to a novel solution named TriangleWad.
arXiv Detail & Related papers (2024-04-10T06:58:58Z)
Private Set Generation with Discriminative Information [63.851085173614]
Differentially private data generation is a promising solution to the data privacy challenge. Existing private generative models are struggling with the utility of synthetic samples. We introduce a simple yet effective method that greatly improves the sample utility of state-of-the-art approaches.
arXiv Detail & Related papers (2022-11-07T10:02:55Z)
Differentially private multivariate medians [5.436813619675772]
We develop novel finite-sample performance guarantees for differentially private depth-based medians.<n>We show that under Cauchy marginals, the cost of heavy-tailed location estimation outweighs the cost of privacy.
arXiv Detail & Related papers (2022-10-12T17:56:04Z)
Private measures, random walks, and synthetic data [7.5764890276775665]
Differential privacy is a mathematical concept that provides an information-theoretic security guarantee. We develop a private measure from a data set that allows us to efficiently construct private synthetic data. A key ingredient in our construction is a new superregular random walk, whose joint distribution of steps is as regular as that of independent random variables.
arXiv Detail & Related papers (2022-04-20T00:06:52Z)
Wasserstein Iterative Networks for Barycenter Estimation [80.23810439485078]
We present an algorithm to approximate the Wasserstein-2 barycenters of continuous measures via a generative model. Based on the celebrity faces dataset, we construct Ave, celeba! dataset which can be used for quantitative evaluation of barycenter algorithms.
arXiv Detail & Related papers (2022-01-28T16:59:47Z)
Differentially Private Sliced Wasserstein Distance [5.330240017302619]
We take the perspective of computing the divergences between distributions under the Differential Privacy (DP) framework. Instead of resorting to the popular gradient-based sanitization method for DP, we tackle the problem at its roots by focusing on the Sliced Wasserstein Distance.
arXiv Detail & Related papers (2021-07-05T08:06:02Z)
A One-Pass Private Sketch for Most Machine Learning Tasks [48.17461258268463]
Differential privacy (DP) is a compelling privacy definition that explains the privacy-utility tradeoff via formal, provable guarantees. We propose a private sketch that supports a multitude of machine learning tasks including regression, classification, density estimation, and more. Our sketch consists of randomized contingency tables that are indexed with locality-sensitive hashing and constructed with an efficient one-pass algorithm.
arXiv Detail & Related papers (2020-06-16T17:47:48Z)
GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators [74.16405337436213]
We propose Gradient-sanitized Wasserstein Generative Adrial Networks (GS-WGAN) GS-WGAN allows releasing a sanitized form of sensitive data with rigorous privacy guarantees. We find our approach consistently outperforms state-of-the-art approaches across multiple metrics.
arXiv Detail & Related papers (2020-06-15T10:01:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.