Journal of Machine Learning Research · 2010 · 696 citations · 0 references
ComputingComputer ScienceMachine LearningOptimizationDimension ReductionDimensionality ReductionMatrix ComputationMatrix FactorizationOptimization For Machine LearningSpectral MethodsLow-rank ApproximationLow-rank OptimizationMatrix CompletionOptimization For High-dimensional DataRegularizationRegularization TechniquesSparse Matrix AlgorithmsSparse Matrix Computation
We use convex relaxation techniques to provide a sequence of regularized low-rank solutions for large-scale matrix completion problems. Using the nuclear norm as a regularizer, we provide a simple ...