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 …

In this paper, we study the problem of learning phylogenies and hidden Markov models. We
call a Markov model nonsingular if all transition matrices have determinants bounded away …

The enormous complexity of biological systems at the molecular level must be answered
with powerful computational methods. Computational biology is a young field, but has seen …

The evolutionary history of a set of species is represented by a phylogenetic tree, which is a
rooted, leaf-labeled tree, where internal nodes represent ancestral species and the leaves …

Inferring evolutionary trees is an interesting and important problem in biology, but one that is
computationally difficult as most associated optimization problems are NP-hard. Although …

We consider the problem of learning mixtures of product distributions over discrete domains
in the distribution learning framework introduced by Kearns et al. Proceedings of the 26 th …

We provide time-and sample-efficient algorithms for learning and testing latent-tree Ising
models, ie Ising models that may only be observed at their leaf nodes. On the learning side …

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 …

We propose and analyze a new vantage point for the learning of mixtures of Gaussians:
namely, the PAC-style model of learning probability distributions introduced by Kearns et …