Sparse Recovery for Earth Mover Distance

• Main Authors: Gupta, Rishi V. (Contributor), Indyk, Piotr (Contributor), Price, Eric C. (Contributor)
• Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor)
• Format: Article
• Language: English
• Published: University of Ilinois at Urbana-Champaign, 2011-05-10T20:03:58Z.
• Subjects: Article
• Online Access: Get fulltext

URL to paper listed on conference site
We initiate the study of sparse recovery problems under the Earth-Mover Distance (EMD). Specically, we design a distribution over m x 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, in some scenarios, shows its advantages over the "usual" recovery in the lp norms.
David & Lucile Packard Foundation
Danish National Research Foundation (MADALGO (Center for Massive Data Algorithmics))
National Science Foundation (U.S.) (grant CCF-0728645)
Charles Stark Draper Laboratory
Cisco Community Fellowship Program
National Science Foundation (U.S.). Graduate Research Fellowship Program