Exact Matrix Completion via Convex Optimization
Emmanuel J. Candès, Benjamin Recht · Foundations of Computational Mathematics · 2009
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.
Cited by 4,877 works. doi:10.1007/s10208-009-9045-5 Open-access PDF
Authors
References
- Random Graphs
- Compressed sensing
- Compressed sensing
- Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
- Topics in Matrix Analysis
- Decoding by Linear Programming
- Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
- Semidefinite Programming
- A Singular Value Thresholding Algorithm for Matrix Completion
- Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization