中文
相关论文

相关论文: Differentially Private Sampling from Distributions…

200 篇论文

Developing machine learning methods that are privacy preserving is today a central topic of research, with huge practical impacts. Among the numerous ways to address privacy-preserving learning, we here take the perspective of computing the…

机器学习 · 计算机科学 2021-07-06 Alain Rakotomamonjy , Liva Ralaivola

Differential privacy (DP) has achieved remarkable results in the field of privacy-preserving machine learning. However, existing DP frameworks do not satisfy all the conditions for becoming metrics, which prevents them from deriving better…

机器学习 · 计算机科学 2024-01-24 Chengyi Yang , Jiayin Qi , Aimin Zhou

In this work, we introduce a novel framework for privately optimizing objectives that rely on Wasserstein distances between data-dependent empirical measures. Our main theoretical contribution is, based on an explicit formulation of the…

机器学习 · 计算机科学 2025-05-22 David Rodríguez-Vítores , Clément Lalanne , Jean-Michel Loubes

Estimating the density of a distribution from samples is a fundamental problem in statistics. In many practical settings, the Wasserstein distance is an appropriate error metric for density estimation. For example, when estimating…

机器学习 · 计算机科学 2024-07-01 Vitaly Feldman , Audra McMillan , Satchit Sivakumar , Kunal Talwar

We develop a projected Wasserstein distance for the two-sample test, a fundamental problem in statistics and machine learning: given two sets of samples, to determine whether they are from the same distribution. In particular, we aim to…

机器学习 · 统计学 2024-04-01 Jie Wang , Rui Gao , Yao Xie

Given a dataset of $n$ i.i.d. samples from an unknown distribution $P$, we consider the problem of generating a sample from a distribution that is close to $P$ in total variation distance, under the constraint of differential privacy (DP).…

数据结构与算法 · 计算机科学 2023-06-23 Badih Ghazi , Xiao Hu , Ravi Kumar , Pasin Manurangsi

Differential Privacy (DP) has become a gold standard in privacy-preserving data analysis. While it provides one of the most rigorous notions of privacy, there are many settings where its applicability is limited. Our main contribution is in…

密码学与安全 · 计算机科学 2021-10-20 Aman Bansal , Rahul Chunduru , Deepesh Data , Manoj Prabhakaran

Local differential privacy (LDP) is increasingly employed in privacy-preserving machine learning to protect user data before sharing it with an untrusted aggregator. Most LDP methods assume that users possess only a single data record,…

机器学习 · 计算机科学 2025-05-05 Behnoosh Zamanlooy , Mario Diaz , Shahab Asoodeh

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…

机器学习 · 计算机科学 2025-10-06 Anming Gu , Sasidhar Kunapuli , Mark Bun , Edward Chien , Kristjan Greenewald

Estimating spatial distributions is important in data analysis, such as traffic flow forecasting and epidemic prevention. To achieve accurate spatial distribution estimation, the analysis needs to collect sufficient user data. However,…

数据库 · 计算机科学 2024-12-12 Leilei Du , Peng Cheng , Libin Zheng , Xiang Lian , Lei Chen , Wei Xi , Wangze Ni

Distribution estimation under local differential privacy (LDP) is a fundamental and challenging task. Significant progresses have been made on categorical data. However, due to different evaluation metrics, these methods do not work well…

机器学习 · 计算机科学 2025-09-25 Puning Zhao , Zhikun Zhang , Bo Sun , Li Shen , Liang Zhang , Shaowei Wang , Zhe Liu

We initiate an investigation of private sampling from distributions. Given a dataset with $n$ independent observations from an unknown distribution $P$, a sampling algorithm must output a single observation from a distribution that is close…

机器学习 · 计算机科学 2022-11-16 Sofya Raskhodnikova , Satchit Sivakumar , Adam Smith , Marika Swanberg

Many algorithms have been developed to estimate probability distributions subject to differential privacy (DP): such an algorithm takes as input independent samples from a distribution and estimates the density function in a way that is…

密码学与安全 · 计算机科学 2024-12-17 Albert Cheu , Debanuj Nayak

Differential dynamic programming (DDP) is a popular technique for solving nonlinear optimal control problems with locally quadratic approximations. However, existing DDP methods are not designed for stochastic systems with unknown…

系统与控制 · 电气工程与系统科学 2023-05-18 Astghik Hakobyan , Insoon Yang

We study the problem of sampling from a distribution under local differential privacy (LDP). Given a private distribution $P \in \mathcal{P}$, the goal is to generate a single sample from a distribution that remains close to $P$ in…

机器学习 · 计算机科学 2025-10-13 Hrad Ghoukasian , Bonwoo Lee , Shahab Asoodeh

The Wasserstein distance is a distance between two probability distributions and has recently gained increasing popularity in statistics and machine learning, owing to its attractive properties. One important approach to extending this…

统计方法学 · 统计学 2022-02-14 Ryo Okano , Masaaki Imaizumi

Gromov--Wasserstein (GW) distances compare graphs, shapes, and point clouds through internal distances, without requiring a common coordinate system. This invariance is powerful, but discrete GW is a nonconvex quadratic optimal transport…

机器学习 · 计算机科学 2026-05-15 Ao Xu , Tieru Wu

We develop a kernel projected Wasserstein distance for the two-sample test, an essential building block in statistics and machine learning: given two sets of samples, to determine whether they are from the same distribution. This method…

统计理论 · 数学 2022-05-10 Jie Wang , Rui Gao , Yao Xie

Wasserstein distance is a key metric for quantifying data divergence from a distributional perspective. However, its application in privacy-sensitive environments, where direct sharing of raw data is prohibited, presents significant…

机器学习 · 计算机科学 2025-02-04 Wenqian Li , Yan Pang

This paper studies the optimization of the KL functional on the Wasserstein space of probability measures, and develops a sampling framework based on Wasserstein gradient descent (WGD). We identify two important subclasses of the…

统计计算 · 统计学 2026-02-04 Van Chien Ta , Thi Mai Hong Chu , Minh-Ngoc Tran
‹ 上一页 1 2 3 10 下一页 ›