Sparse recovery for Earth Mover Distance
Lists
Only you see this
Abstract
We initiate the study of sparse recovery problems under the Earth-Mover Distance (EMD). Specifically, we design a distribution over m × n matrices A, for m ≪ n, such that for any x, given Ax, we can recover a k-sparse approximation to x under the EMD distance. We also provide an empirical evaluation of the method that show, in some scenarios, its advantages over the “usual” recovery in the ℓp norms.
BibTeX
@inproceedings{gupta2010sparse,
author = {Rishi Gupta and Piotr Indyk and Eric Price},
title = {{Sparse recovery for Earth Mover Distance}},
booktitle = {Allerton},
year = {2010},
url = {https://openreview.net/forum?id=Ygr99HR8tK},
}Loading related content...