Exact Matrix Completion via Convex Optimization (English)

In: Foundations of Computational Mathematics   ;  9 ,  6  ;  717-772  ;  2009

How to get this document?

Free access

Abstract We consider a problem of considerable practical interest: the recovery of a data matrix from a sampling of its entries. Suppose that we observe m entries selected uniformly at random from a matrix M. Can we complete the matrix and recover the entries that we have not seen? We show that one can perfectly recover most low-rank matrices from what appears to be an incomplete set of entries. We prove that if the number m of sampled entries obeys $$m\ge C\,n^{1.2}r\log n$$ for some positive numerical constant C, then with very high probability, most n×n matrices of rank r can be perfectly recovered by solving a simple convex optimization program. This program finds the matrix with minimum nuclear norm that fits the data. The condition above assumes that the rank is not too large. However, if one replaces the 1.2 exponent with 1.25, then the result holds for all values of the rank. Similar results hold for arbitrary rectangular matrices as well. Our results are connected with the recent literature on compressed sensing, and show that objects other than signals and images can be perfectly reconstructed from very limited information.

Table of contents – Volume 9, Issue 6

Show all volumes and issues

The tables of contents are generated automatically and are based on the data records of the individual contributions available in the index of the TIB portal. The display of the Tables of Contents may therefore be incomplete.

Sufficient Set of Integrability Conditions of an Orthonomic System
Marvan, Michal | 2009
Convergent Interpolation to Cauchy Integrals over Analytic Arcs
Baratchart, Laurent / Yattselev, Maxim | 2009
Exact Matrix Completion via Convex Optimization
Candès, Emmanuel J. / Recht, Benjamin | 2009