arXiv (Cornell University) · 2015 · 144 citations · 26 references
ComputingComputer ScienceAlgorithmsOptimizationSensor FusionConvex OptimizationDimensionality ReductionMatrix ComputationNumerical AlgorithmsNumerical AnalysisNumerical Linear AlgebraConvergenceGradient DescentLow-rank ApproximationLow-rank OptimizationLow-rank ReconstructionSparse Inverse ProblemsSparse Matrix AlgorithmsSparse Matrix Computation
In this paper we study the problem of recovering a low-rank matrix from linear measurements. Our algorithm, which we call Procrustes Flow, starts from an initial estimate obtained by a thresholding scheme followed by gradient descent on a non-convex objective. We show that as long as the measurements obey a standard restricted isometry property, our algorithm converges to the unknown matrix at a geometric rate. In the case of Gaussian measurements, such convergence occurs for a $n_1 \times n_2$ matrix of rank $r$ when the number of measurements exceeds a constant times $(n_1+n_2)r$.
26