中文
相关论文

相关论文: Archimedes Meets Privacy: On Privately Estimating …

200 篇论文

We study the relationship between adversarial robustness and differential privacy in high-dimensional algorithmic statistics. We give the first black-box reduction from privacy to robustness which can produce private estimators with optimal…

数据结构与算法 · 计算机科学 2024-06-18 Samuel B. Hopkins , Gautam Kamath , Mahbod Majid , Shyam Narayanan

We give the first polynomial time and sample $(\epsilon, \delta)$-differentially private (DP) algorithm to estimate the mean, covariance and higher moments in the presence of a constant fraction of adversarial outliers. Our algorithm…

机器学习 · 统计学 2021-12-08 Pravesh K. Kothari , Pasin Manurangsi , Ameya Velingker

We study person-level differentially private (DP) mean estimation in the case where each person holds multiple samples. DP here requires the usual notion of distributional stability when $\textit{all}$ of a person's datapoints can be…

数据结构与算法 · 计算机科学 2024-07-22 Sushant Agarwal , Gautam Kamath , Mahbod Majid , Argyris Mouzakis , Rose Silver , Jonathan Ullman

Differentially private federated learning is crucial for maintaining privacy in distributed environments. This paper investigates the challenges of high-dimensional estimation and inference under the constraints of differential privacy.…

机器学习 · 统计学 2024-04-26 Zhe Zhang , Ryumei Nakada , Linjun Zhang

With the development of big data and machine learning, privacy concerns have become increasingly critical, especially when handling heterogeneous datasets containing sensitive personal information. Differential privacy provides a rigorous…

机器学习 · 统计学 2025-08-08 Ziliang Shen , Caixing Wang , Shaoli Wang , Yibo Yan

We study statistical estimation under local differential privacy (LDP) when users may hold heterogeneous privacy levels and accuracy must be guaranteed with high probability. Departing from the common in-expectation analyses, and for…

机器学习 · 统计学 2025-10-15 Maryam Aliakbarpour , Alireza Fallah , Swaha Roy , Ria Stevens

In this work, we study high-dimensional mean estimation under user-level differential privacy, and design an $(\varepsilon,\delta)$-differentially private mechanism using as few users as possible. In particular, we provide a nearly optimal…

数据结构与算法 · 计算机科学 2022-06-14 Hossein Esfandiari , Vahab Mirrokni , Shyam Narayanan

We study the fundamental task of estimating the median of an underlying distribution from a finite number of samples, under pure differential privacy constraints. We focus on distributions satisfying the minimal assumption that they have a…

Private data analysis faces a significant challenge known as the curse of dimensionality, leading to increased costs. However, many datasets possess an inherent low-dimensional structure. For instance, during optimization via gradient…

机器学习 · 计算机科学 2024-10-29 Eliad Tsfadia

In this work, we give efficient algorithms for privately estimating a Gaussian distribution in both pure and approximate differential privacy (DP) models with optimal dependence on the dimension in the sample complexity. In the pure DP…

数据结构与算法 · 计算机科学 2023-06-02 Daniel Alabi , Pravesh K. Kothari , Pranay Tankala , Prayaag Venkat , Fred Zhang

We study differentially private mean estimation in a high-dimensional setting. Existing differential privacy techniques applied to large dimensions lead to computationally intractable problems or estimators with excessive privacy loss.…

机器学习 · 计算机科学 2020-07-23 Aditya Dhar , Jason Huang

The simplest and most widely applied method for guaranteeing differential privacy is to add instance-independent noise to a statistic of interest that is scaled to its global sensitivity. However, global sensitivity is a worst-case notion…

统计理论 · 数学 2019-06-10 Mark Bun , Thomas Steinke

We develop differentially private methods for estimating various distributional properties. Given a sample from a discrete distribution $p$, some functional $f$, and accuracy and privacy parameters $\alpha$ and $\varepsilon$, the goal is to…

数据结构与算法 · 计算机科学 2018-03-02 Jayadev Acharya , Gautam Kamath , Ziteng Sun , Huanyu Zhang

Bayesian methods lie at the heart of modern data science and provide a powerful scaffolding for estimation in data-constrained settings and principled quantification and propagation of uncertainty. Yet in many real-world use cases where…

数据结构与算法 · 计算机科学 2026-03-20 Sitan Chen , Jingqiu Ding , Mahbod Majid , Walter McKelvie

Estimating the quantiles of a large dataset is a fundamental problem in both the streaming algorithms literature and the differential privacy literature. However, all existing private mechanisms for distribution-independent quantile…

数据结构与算法 · 计算机科学 2022-01-11 Daniel Alabi , Omri Ben-Eliezer , Anamay Chaturvedi

The challenge of producing accurate statistics while respecting the privacy of the individuals in a sample is an important area of research. We study minimax lower bounds for classes of differentially private estimators. In particular, we…

机器学习 · 计算机科学 2024-09-19 Clément Lalanne , Aurélien Garivier , Rémi Gribonval

We present new differentially private algorithms for learning a large-margin halfspace. In contrast to previous algorithms, which are based on either differentially private simulations of the statistical query model or on private convex…

机器学习 · 计算机科学 2020-02-25 Huy L. Nguyen , Jonathan Ullman , Lydia Zakynthinou

We study the optimal sample complexity of a given workload of linear queries under the constraints of differential privacy. The sample complexity of a query answering mechanism under error parameter $\alpha$ is the smallest $n$ such that…

数据结构与算法 · 计算机科学 2016-12-12 Assimakis Kattis , Aleksandar Nikolov

Fueled by the ever-increasing need for statistics that guarantee the privacy of their training sets, this article studies the centrally-private estimation of Sobolev-smooth densities of probability over the hypercube in dimension d. The…

统计理论 · 数学 2024-09-17 Clément Lalanne , Sébastien Gadat

The privacy of data is a major challenge in machine learning as a trained model may expose sensitive information of the enclosed dataset. Besides, the limited computation capability and capacity of edge devices have made cloud-hosted…

机器学习 · 计算机科学 2020-05-15 Behnam Khaleghi , Mohsen Imani , Tajana Rosing
‹ 上一页 1 2 3 10 下一页 ›