PubMed · 2015 · 119 citations · 22 references
ComputingComputer ScienceAlgorithmsOptimizationSensor FusionConvex OptimizationMatrix ComputationMatrix FactorizationConvex RelaxationsLow-rank OptimizationNon-negative Matrix FactorizationNonconvex OptimizationOptimization AlgorithmsSensingSparse Matrix Algorithms
We study the estimation of low rank matrices via nonconvex optimization. Compared with convex relaxation, nonconvex optimization exhibits superior empirical performance for large scale instances of low rank matrix estimation. However, the understanding of its theoretical guarantees are limited. In this paper, we define the notion of projected oracle divergence based on which we establish sufficient conditions for the success of nonconvex optimization. We illustrate the consequences of this general framework for matrix sensing. In particular, we prove that a broad class of nonconvex optimization algorithms, including alternating minimization and gradient-type methods, geometrically converge to the global optimum and exactly recover the true low rank matrices under standard conditions.
22
Mathematics and Computers in Simulation · 1991 · 2.5K citations
Low-rank matrix completion using alternating minimization
Prateek Jain, Praneeth Netrapalli, Sujay Sanghavi · 2013 · 878 citations