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

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 consider the problem of learning a mixture of linear regressions (MLRs). An MLR is
specified by k nonnegative mixing weights p 1,…, pk summing to 1, and k unknown …

We design a new, fast algorithm for agnostically learning univariate probability distributions
whose densities are well-approximated by piecewise polynomial functions. Let ƒ be the …

As we apply machine learning to more and more important tasks, it becomes increasingly
important that these algorithms are robust to systematic, or worse, malicious, noise. Despite …

This work initiates a systematic investigation of testing\em high-dimensional structured
distributions by focusing on testing\em Bayesian networks–the prototypical family of directed …

We develop a framework that leverages the smoothed complexity analysis by Spielman and
Teng to circumvent paradoxes and impossibility theorems in social choice, motivated by …

The Poisson Binomial Distribution-Old & New Page 1 Statistical Science 2023, Vol. 38, No. 1,
108–119 https://doi.org/10.1214/22-STS852 © Institute of Mathematical Statistics, 2023 The …

Suppose a presidential election between two alternatives (candidates) a and b will be held
soon, and there are n agents (voters). Each agent independently votes for an alternative with …