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 study the question of testing structured properties (classes) of discrete distributions.
Specifically, given sample access to an arbitrary distribution D over n and a property PP, 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 …

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 …

We study the problem, introduced by Qiao and Valiant, of learning from untrusted batches.
Here, we assume m users, all of whom have samples from some underlying distribution over …

An (n, k)-Poisson Multinomial Distribution (PMD) is a random variable of the form X=∑ i= 1 n
X i, where the X i's are independent random vectors supported on the set of standard basis …

We study the problem of covering and learning sums $ X= X_1+\cdots+ X_n $ of
independent integer-valued random variables $ X_i $(SIIRVs) with infinite support. De et al …