Near-optimal Differentially Private Principal Components

By Kamalika Chaudhuri, Anand D. Sarwate, Kaushik Sinha. 2012

165 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Extremal Mechanisms for Local Differential Privacy (2014, methodology): “The typical recipe is to propose a differentially private mechanism inspired by [11, 13, 26, 20], and then establish its near-optimality by comparing the achievable utility to a converse, for example in principal component analysis [8, 5, 19, 24], linear queries [21, 18], logistic regression [7] and”
Private selection from private candidates (2018, background): “Some examples include private PAC learning [20], private frequent itemset mining [4], private PCA [7, 19] and private multiple hypothesis testing [14, 35].”
Certified Data Removal from Machine Learning Models (2019, background): “Many classical machine learning algorithms have been shown to support differentially private versions, including PCA (Chaudhuri et al., 2012), matrix fac- torization (Liu et al., 2015), linear models (Chaudhuri et al., 2011), and neural networks (Abadi et al., 2016).”
Analyze gauss: optimal bounds for privacy-preserving principal component analysis (2014, background): “larity of the privacy guarantee, protecting, variously, the privacy of each row in its entirety [4, 14, 21, 9], which is what we do here, or individual entries [23, 18], or norm 1 changes to any row [17].”
Beyond worst-case analysis in private singular vector computation (2012, methodology): “[11] also give a polynomial time algorithm for performing this sampling from the exponential mechanism, whereas [5] give a heuristic, but practical implementation using Markov-Chain Monte-Carlo.”
A Comprehensive Survey of Privacy-preserving Federated Learning (2021, methodology): “DP-based PPML methods can be divided into two categories: privacy-preserving models designed by adding noise to the trained model [22, 85], and privacy-preserving models designed by adding noise to the objective function [21, 219].”
Privacy-preserving Analysis of Correlated Data (2016, background): “…et al., 2006), and there is a growing body of work on differentially private learning algorithms (Chaudhuri et al., 2011; Jain et al., 2012; Kifer et al., 2012; Chaudhuri et al., 2012; Hardt and Roth, 2013; Wang et al., 2015; Duchi et al., 2013; Bassily et al., 2014; Imtiaz and Sarwate, 2015).”
Differentially Private Empirical Risk Minimization Revisited: Faster and More General (2018, background): “For non-convex problem under differential privacy, [15][9][13] studied private SVD.”
The Algorithmic Foundations of Differential Privacy (2014, methodology): “Spectral learning techniques, including PCA and low rank matrix approximation have also been studied [7, 14, 33, 42, 43, 51].”
Optimal Noise-Adding Mechanism in Additive Differential Privacy (2018, methodology): “…learning (Shokri and Shmatikov, 2015; Abadi et al., 2016; Phan et al., 2016; Agarwal et al., 2018), hypothesis testing (Sheffet, 2018), matrix completion (Jain et al., 2018), expectation maximization (Park et al., 2017), and principal component analysis (Chaudhuri et al., 2012; Ge et al., 2018).”
Minimax Filter: Learning to Preserve Privacy from Inference Attacks (2016, background): “In addition, the learned ﬁlters contain information about private data analogous to learned PCA components revealing information about data (Chaudhuri et al., 2012), and require further sanitization if the ﬁlters are released to a third party.”
Differentially private multi-party computation (2014, methodology): “classification [27, 9], k-means clustering [4], principal component analysis [7, 8, 23, 26].”
Profile-based Privacy for Locally Private Computations (2019, background): “A body of compelling results [4, 5, 13, 10, 18] have been achieved in the ”centralized” model, in which a trusted data curator has raw access to the data while performing the privacy-preserving operations.”
Differential Privacy and Machine Learning: a Survey and Review (2014, methodology): “[7] proposes an ǫ-differentially private mechanism, PPCA, to compute k largest eigenvectors at the same time.”