Advances and open problems in federated learning
Federated learning (FL) is a machine learning setting where many clients (eg, mobile
devices or whole organizations) collaboratively train a model under the orchestration of a …
devices or whole organizations) collaboratively train a model under the orchestration of a …
Why is public pretraining necessary for private model training?
In the privacy-utility tradeoff of a model trained on benchmark language and vision tasks,
remarkable improvements have been widely reported when the model is pretrained on …
remarkable improvements have been widely reported when the model is pretrained on …
Efficient mean estimation with pure differential privacy via a sum-of-squares exponential mechanism
We give the first polynomial-time algorithm to estimate the mean of ad-variate probability
distribution with bounded covariance from Õ (d) independent samples subject to pure …
distribution with bounded covariance from Õ (d) independent samples subject to pure …
Private distribution learning with public data: The view from sample compression
We study the problem of private distribution learning with access to public data. In this setup,
which we refer to as* public-private learning*, the learner is given public and private …
which we refer to as* public-private learning*, the learner is given public and private …
Private estimation with public data
We initiate the study of differentially private (DP) estimation with access to a small amount of
public data. For private estimation of $ d $-dimensional Gaussians, we assume that the …
public data. For private estimation of $ d $-dimensional Gaussians, we assume that the …
A private and computationally-efficient estimator for unbounded gaussians
We give the first polynomial-time, polynomial-sample, differentially private estimator for the
mean and covariance of an arbitrary Gaussian distribution $ N (\mu,\Sigma) $ in $\R^ d $. All …
mean and covariance of an arbitrary Gaussian distribution $ N (\mu,\Sigma) $ in $\R^ d $. All …
New lower bounds for private estimation and a generalized fingerprinting lemma
We prove new lower bounds for statistical estimation tasks under the constraint of
$(\varepsilon,\delta) $-differential privacy. First, we provide tight lower bounds for private …
$(\varepsilon,\delta) $-differential privacy. First, we provide tight lower bounds for private …
Decision tree for locally private estimation with public data
We propose conducting locally differentially private (LDP) estimation with the aid of a small
amount of public data to enhance the performance of private estimation. Specifically, we …
amount of public data to enhance the performance of private estimation. Specifically, we …
A polynomial time, pure differentially private estimator for binary product distributions
V Singhal - International Conference on Algorithmic …, 2024 - proceedings.mlr.press
We present the first $\varepsilon $-differentially private, computationally efficient algorithm
that estimates the means of product distributions over $\{0, 1\}^ d $ accurately in total …
that estimates the means of product distributions over $\{0, 1\}^ d $ accurately in total …
Leveraging public representations for private transfer learning
Motivated by the recent empirical success of incorporating public data into differentially
private learning, we theoretically investigate how a shared representation learned from …
private learning, we theoretically investigate how a shared representation learned from …