We study the problem of private distribution learning with access to pub...
Indiscriminate data poisoning attacks aim to decrease a model's test acc...
Differentially private stochastic gradient descent privatizes model trai...
We show that the canonical approach for training differentially private ...
The canonical algorithm for differentially private mean estimation is to...
We introduce camouflaged data poisoning attacks, a new attack vector tha...
The performance of differentially private machine learning can be booste...
We study the relationship between adversarial robustness and differentia...
We initiate the study of differentially private (DP) estimation with acc...
Differentially private stochastic gradient descent (DP-SGD) is the workh...
We prove new lower bounds for statistical estimation tasks under the
con...
Data poisoning attacks, in which a malicious adversary aims to influence...
Reviewers in peer review are often miscalibrated: they may be strict,
le...
We give the first polynomial-time algorithm to estimate the mean of a
d-...
Hyperparameter optimization is a ubiquitous challenge in machine learnin...
We give the first polynomial-time, polynomial-sample, differentially pri...
We present a method for producing unbiased parameter estimates and valid...
We give simpler, sparser, and faster algorithms for differentially priva...
We study stochastic convex optimization with heavy-tailed data under the...
We study the problem of forgetting datapoints from a learnt model. In th...
We provide sample complexity upper bounds for agnostically learning
mult...
A common pain point in differentially private machine learning is the
si...
We present simple differentially private estimators for the mean and
cov...
Differentially private statistical estimation has seen a flurry of
devel...
We show how to efficiently provide differentially private answers to cou...
In hypothesis testing, a false discovery occurs when a hypothesis is
inc...
We initiate the study of hypothesis selection under local differential
p...
We give new upper and lower bounds on the minimax sample complexity of
d...
We consider the problem of learning Markov Random Fields (including the
...
We give a nearly-optimal algorithm for testing uniformity of distributio...
Learning the parameters of a Gaussian mixtures models is a fundamental a...
We provide a differentially private algorithm for hypothesis selection. ...
In this work we present novel differentially private identity
(goodness-...
Hypothesis testing plays a central role in statistical inference, and is...
We investigate distribution testing with access to non-adaptive conditio...
We design nearly optimal differentially private algorithms for learning ...
In high dimensions, most machine learning methods are brittle to even a ...
We develop differentially private methods for estimating various
distrib...
A generative model may generate utter nonsense when it is fit to maximiz...
We prove near-tight concentration of measure for polynomial functions of...
We study the fundamental problem of learning the parameters of a
high-di...
Robust estimation is much more challenging in high dimensions than it is...
We study high-dimensional distribution learning in an agnostic setting w...