Eric Price

Publications
Influence

Equality of Opportunity in Supervised Learning

Moritz Hardt, Eric Price, Nathan Srebro
Computer Science, Mathematics
NIPS
7 October 2016

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

1,370
278
PDF

Compressed Sensing using Generative Models

Ashish Bora, A. Jalal, Eric Price, A. Dimakis
Computer Science, Mathematics
ICML
9 March 2017

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

Simple and practical algorithm for sparse Fourier transform

Haitham Hassanieh, P. Indyk, D. Katabi, Eric Price
Computer Science, Mathematics
SODA
17 January 2012

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

Nearly optimal sparse fourier transform

Haitham Hassanieh, P. Indyk, D. Katabi, Eric Price
Mathematics, Computer Science
STOC '12
12 January 2012

We consider the problem of computing the k-sparse approximation to the discrete Fourier transform of an n-dimensional signal. Expand

The Noisy Power Method: A Meta Algorithm with Applications

Moritz Hardt, Eric Price
Computer Science, Mathematics
NIPS
11 November 2013

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

AmbientGAN: Generative models from lossy measurements

Ashish Bora, Eric Price, A. Dimakis
Computer Science
ICLR
15 February 2018

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

Adversarial examples from computational constraints

Sébastien Bubeck, Eric Price, Ilya P. Razenshteyn
Computer Science, Mathematics
ICML
25 May 2018

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

Compressed Sensing with Deep Image Prior and Learned Regularization

Dave Van Veen, A. Jalal, Eric Price, S. Vishwanath, A. Dimakis
Computer Science, Mathematics
ArXiv
17 June 2018

We propose a novel method for compressed sensing recovery using untrained deep generative models. Expand

Lower bounds for sparse recovery

Khanh Do Ba, P. Indyk, Eric Price, David P. Woodruff
Computer Science, Mathematics
SODA '10
17 January 2010

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

Tight Bounds for Learning a Mixture of Two Gaussians

Moritz Hardt, Eric Price
Computer Science, Mathematics
STOC
19 April 2014

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

Recommended Authors