Add to ORKGWe develop a framework for efficiently transforming certain approximation algorithms into differentially-private variants, in a black-box manner. Our results focus on algorithms A that output an approximation to a function f of the form $(1-a)f(x)-k <= A(x) <= (1+a)f(x)+k$, where 0<=a <1 is a parameter that can be``tuned" to small-enough values while incurring only a poly blowup in the running time/space. We show that such algorithms can be made DP without sacrificing accuracy, as long as the function f has small global sensitivity. We achieve these results by applying the smooth sensitivity framework developed by Nissim, Raskhodnikova, and Smith (STOC 2007). Our framework naturally applies to transform non-private FPRAS (resp. FPTAS) alg...
Differentially private algorithms allow large-scale data analytics while preserving user privacy. De...
A central challenge in differential privacy is to design computationally efficient non-interactive a...
In this paper, we study the Empirical Risk Minimization (ERM) problem in the non-interactive Local ...
We develop a framework for efficiently transforming certain approximation algorithms into differenti...
The exponential increase in the amount of available data makes taking advantage of them without viol...
Collecting user data is crucial for advancing machine learning, social science, and government polic...
We initiate a systematic study of algorithms that are both differentially-private and run in subline...
We consider the problem of designing and analyzing differentially private algorithms that can be imp...
We give the first differentially private algorithms that estimate a variety of geometric features of...
We study functionally private approximations. An approximation function $g$ is {em functionally priv...
Differential privacy (DP) is a key tool in privacy-preserving data analysis. Yet it remains challeng...
We study the problem of differentially private (DP) fine-tuning of large pre-trained models -- a rec...
In this paper, we introduce a new notion of guaranteed privacy that requires that the change of the ...
We prove new upper and lower bounds on the sample complexity of (ε, δ) differentially private algori...
Consider the following problem: given a metric space, some of whose points are ``clients,\u27\u27 se...
Differentially private algorithms allow large-scale data analytics while preserving user privacy. De...
A central challenge in differential privacy is to design computationally efficient non-interactive a...
In this paper, we study the Empirical Risk Minimization (ERM) problem in the non-interactive Local ...
We develop a framework for efficiently transforming certain approximation algorithms into differenti...
The exponential increase in the amount of available data makes taking advantage of them without viol...
Collecting user data is crucial for advancing machine learning, social science, and government polic...
We initiate a systematic study of algorithms that are both differentially-private and run in subline...
We consider the problem of designing and analyzing differentially private algorithms that can be imp...
We give the first differentially private algorithms that estimate a variety of geometric features of...
We study functionally private approximations. An approximation function $g$ is {em functionally priv...
Differential privacy (DP) is a key tool in privacy-preserving data analysis. Yet it remains challeng...
We study the problem of differentially private (DP) fine-tuning of large pre-trained models -- a rec...
In this paper, we introduce a new notion of guaranteed privacy that requires that the change of the ...
We prove new upper and lower bounds on the sample complexity of (ε, δ) differentially private algori...
Consider the following problem: given a metric space, some of whose points are ``clients,\u27\u27 se...
Differentially private algorithms allow large-scale data analytics while preserving user privacy. De...
A central challenge in differential privacy is to design computationally efficient non-interactive a...
In this paper, we study the Empirical Risk Minimization (ERM) problem in the non-interactive Local ...