We propose a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features.Expand

The goal of compressed sensing is to estimate a vector from an underdetermined system of linear measurements, by making use of prior knowledge on the structure of vectors in the relevant domain.Expand

We consider the sparse Fourier transform problem: given a complex vector x of length n, and a parameter k, estimate the k largest (in magnitude) coefficients of the Fourier Transform of x.Expand

We provide a new robust convergence analysis of the well-known power method for computing the dominant singular vectors of a matrix when a significant amount noise is introduced after each matrix-vector multiplication.Expand

We show that the true underlying distribution can be provably recovered even in the presence of per-sample information loss for a class of measurement models.Expand

We show that, for a broad set of classification tasks, the mere existence of a robust classifier implies that it can be found by a possibly exponential-time algorithm with relatively few training examples.Expand

We consider the following <i>k</i>-sparse recovery problem: design an<i>Ax</i>, such that for any signal < i>x</i>> we can efficiently recover x satisfying ||<sub>i</sub> -- x||<sub><i>C</i></sub> ≤ <i>[sub>1</sub>.Expand

We consider the problem of identifying the parameters of an unknown mixture of two arbitrary d-dimensional gaussians from a sequence of independent random samples.Expand