We study high-dimensional distribution learning in an agnostic setting where an adversary is
allowed to arbitrarily corrupt an ε-fraction of the samples. Such questions have a rich history …

We focus on some specific problems in distribution testing, taking goodness-of-fit as a
running example. In particular, we do not aim to provide a comprehensive summary of all the …

We describe a general technique that yields the first Statistical Query lower bounds for a
range of fundamental high-dimensional learning problems involving Gaussian distributions …

The field of property testing originated in work on program checking, and has evolved into
an established and very active research area. In this work, we survey the developments of …

Property testing is concerned with the design of super-fast algorithms for the structural
analysis of large quantities of data. The aim is to unveil global features of the data, such as …

We prove new upper and lower bounds on the sample complexity of (ε, δ) differentially
private algorithms for releasing approximate answers to threshold functions. A threshold …

Many conventional statistical procedures are extremely sensitive to seemingly minor
deviations from modeling assumptions. This problem is exacerbated in modern high …

We provide a differentially private algorithm for hypothesis selection. Given samples from an
unknown probability distribution $ P $ and a set of $ m $ probability distributions $\mathcal …

We give a computationally efficient semi-agnostic algorithm for learning univariate
probability distributions that are well approximated by piecewise polynomial density …

We consider a basic problem in unsupervised learning: learning an unknown Poisson
Binomial Distribution. A Poisson Binomial Distribution (PBD) over {0, 1,..., n} is the …