No spurious local minima in nonconvex low rank problems: A unified geometric analysis

Keyphrases

• Non-convexity 100%
• Geometric Analysis 100%
• Low-rank 100%
• Matrix Completion 100%
• Spurious Local Minima 100%
• Robust Principal Component Analysis 66%
• Sensing Matrix 66%
• Matrix Sensing 66%
• High-order 33%
• Local Minima 33%
• SIMPLE Algorithm 33%
• Globally Optimal 33%
• Nonconvex Objective Function 33%
• Symmetric Matrices 33%
• Stochastic Gradient Descent 33%
• Low-rank Matrix 33%
• Optimization Landscape 33%
• Matrix Problem 33%
• Asymmetric Case 33%
• Asymmetric Matrices 33%

Mathematics

• Matrix (Mathematics) 100%
• Complete Matrix 100%
• Local Minimum 100%
• Asymmetric 66%
• Principal Component Analysis 66%
• Convex 66%
• Saddle Point 33%
• Stochastics 33%
• Objective Function 33%
• Symmetric Matrix 33%