中文
相关论文

相关论文: Private Center Points and Learning of Halfspaces

200 篇论文

While machine learning has proven to be a powerful data-driven solution to many real-life problems, its use in sensitive domains has been limited due to privacy concerns. A popular approach known as **differential privacy** offers provable…

机器学习 · 统计学 2016-04-28 Yu-Xiang Wang , Jing Lei , Stephen E. Fienberg

The problem of learning threshold functions is a fundamental one in machine learning. Classical learning theory implies sample complexity of $O(\xi^{-1} \log(1/\beta))$ (for generalization error $\xi$ with confidence $1-\beta$). The private…

机器学习 · 计算机科学 2022-11-14 Edith Cohen , Xin Lyu , Jelani Nelson , Tamás Sarlós , Uri Stemmer

In this work we analyze the sample complexity of classification by differentially private algorithms. Differential privacy is a strong and well-studied notion of privacy introduced by Dwork et al. (2006) that ensures that the output of an…

数据结构与算法 · 计算机科学 2015-09-15 Vitaly Feldman , David Xiao

We initiate the study of differentially private learning in the proportional dimensionality regime, in which the number of data samples $n$ and problem dimension $d$ approach infinity at rates proportional to one another, meaning that…

机器学习 · 计算机科学 2025-02-20 Cynthia Dwork , Pranay Tankala , Linjun Zhang

A basic problem in the design of privacy-preserving algorithms is the private maximization problem: the goal is to pick an item from a universe that (approximately) maximizes a data-dependent function, all under the constraint of…

机器学习 · 计算机科学 2014-09-09 Kamalika Chaudhuri , Daniel Hsu , Shuang Song

Much of the literature on differential privacy focuses on item-level privacy, where loosely speaking, the goal is to provide privacy per item or training example. However, recently many practical applications such as federated learning…

机器学习 · 计算机科学 2021-01-13 Yuhan Liu , Ananda Theertha Suresh , Felix Yu , Sanjiv Kumar , Michael Riley

Models need to be trained with privacy-preserving learning algorithms to prevent leakage of possibly sensitive information contained in their training data. However, canonical algorithms like differentially private stochastic gradient…

机器学习 · 计算机科学 2022-10-06 Yannis Cattan , Christopher A. Choquette-Choo , Nicolas Papernot , Abhradeep Thakurta

Minimizing a convex risk function is the main step in many basic learning algorithms. We study protocols for convex optimization which provably leak very little about the individual data points that constitute the loss function.…

机器学习 · 计算机科学 2020-08-11 Di Wang , Adam Smith , Jinhui Xu

In the classic point location problem, one is given an arbitrary dataset $X \subset \mathbb{R}^d$ of $n$ points with query access to an unknown halfspace $f : \mathbb{R}^d \to \{0,1\}$, and the goal is to learn the label of every point in…

数据结构与算法 · 计算机科学 2025-09-26 Hadley Black , Kasper Green Larsen , Arya Mazumdar , Barna Saha , Geelon So

A private learner is trained on a sample of labeled points and generates a hypothesis that can be used for predicting the labels of newly sampled points while protecting the privacy of the training set [Kasiviswannathan et al., FOCS 2008].…

机器学习 · 计算机科学 2023-05-17 Moni Naor , Kobbi Nissim , Uri Stemmer , Chao Yan

We develop lower bounds for estimation under local privacy constraints---including differential privacy and its relaxations to approximate or R\'{e}nyi differential privacy---by showing an equivalence between private estimation and…

统计理论 · 数学 2019-05-07 John Duchi , Ryan Rogers

We revisit the problem of finding a minimum enclosing ball with differential privacy: Given a set of $n$ points in the Euclidean space $\mathbb{R}^d$ and an integer $t\leq n$, the goal is to find a ball of the smallest radius $r_{opt}$…

数据结构与算法 · 计算机科学 2017-07-18 Kobbi Nissim , Uri Stemmer

We study the problem of unlearning datapoints from a learnt model. The learner first receives a dataset $S$ drawn i.i.d. from an unknown distribution, and outputs a model $\widehat{w}$ that performs well on unseen samples from the same…

机器学习 · 计算机科学 2021-07-23 Ayush Sekhari , Jayadev Acharya , Gautam Kamath , Ananda Theertha Suresh

Local differential privacy (LDP) is a model where users send privatized data to an untrusted central server whose goal it to solve some data analysis task. In the non-interactive version of this model the protocol consists of a single round…

机器学习 · 计算机科学 2020-09-24 Yuval Dagan , Vitaly Feldman

The hybrid-model (Avent et al 2017) in Differential Privacy is a an augmentation of the local-model where in addition to N local-agents we are assisted by one special agent who is in fact a curator holding the sensitive details of n…

机器学习 · 计算机科学 2022-06-17 Refael Kohen , Or Sheffet

The Shapley value has been proposed as a solution to many applications in machine learning, including for equitable valuation of data. Shapley values are computationally expensive and involve the entire dataset. The query for a point's…

机器学习 · 计算机科学 2022-06-02 Lauren Watson , Rayna Andreeva , Hao-Tsung Yang , Rik Sarkar

Online learning has been in the spotlight from the machine learning society for a long time. To handle massive data in Big Data era, one single learner could never efficiently finish this heavy task. Hence, in this paper, we propose a novel…

机器学习 · 计算机科学 2015-06-24 Chencheng Li , Pan Zhou

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

This paper studies the problem of clustering in metric spaces while preserving the privacy of individual data. Specifically, we examine differentially private variants of the k-medians and Euclidean k-means problems. We present polynomial…

数据结构与算法 · 计算机科学 2020-08-31 Matthew Jones , Huy Lê Nguyen , Thy Nguyen

Differential Privacy offers strong guarantees such as immutable privacy under post processing. Thus it is often looked to as a solution to learning on scattered and isolated data. This work focuses on supervised manifold learning, a…

机器学习 · 计算机科学 2021-10-06 Praneeth Vepakomma , Julia Balla , Ramesh Raskar