Weak Recovery Conditions from Graph Partitioning Bounds and Order Statistics

TITLE: Weak Recovery Conditions from Graph Partitioning Bounds and Order Statistics.

AUTHORS: Alexandre d'Aspremont, Noureddine El Karoui

ABSTRACT: We study a weaker formulation of the nullspace property which guarantees recovery of sparse signals from linear measurements by l_1 minimization. We require this condition to hold only with high probability, given a distribution on the nullspace of the coding matrix A. Under some assumptions on the distribution of the reconstruction error, we show that testing these weak conditions means bounding the optimal value of two classical graph partitioning problems: the k-Dense-Subgraph and MaxCut problems. Both problems admit efficient, relatively tight relaxations and we use semidefinite relaxation techniques to produce tractable bounds. We test the performance of our results on several families of coding matrices.

STATUS: In preparation.

ArXiv PREPRINT: 1004.5151

PAPER: Weak Recovery Conditions from Graph Partitioning Bounds and Order Statistics in pdf