Model-free Nonconvex Matrix Completion: Local Minima Analysis and Applications in Memory-efficient Kernel PCA

zbMath1441.62157arXiv1711.01742MaRDI QIDQ5214234

No author found.

Publication date: 7 February 2020

Full work available at URL: https://arxiv.org/abs/1711.01742

zbMATH Keywords

matrix completionnonconvex optimizationlow-rank approximationmodel-free analysiskernel principal component analysis (PCA)local minimum analysis

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Nonconvex programming, global optimization (90C26) Matrix equations and identities (15A24)

Related Items

Spurious Valleys, NP-Hardness, and Tractability of Sparse Matrix Factorization with Fixed Support, Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization, Unnamed Item

Uses Software

• Wirtinger Flow

Cites Work

• Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions
• Sharp nonasymptotic bounds on the norm of random matrices with independent entries
• Optimal rates of convergence for noisy sparse phase retrieval via thresholded Wirtinger flow
• A nonlinear programming algorithm for solving semidefinite programs via low-rank factorization
• A geometric analysis of phase retrieval
• Rapid, robust, and reliable blind deconvolution via nonconvex optimization
• Matrix estimation by universal singular value thresholding
• First-order methods almost always avoid strict saddle points
• Minimization of functions having Lipschitz continuous first partial derivatives
• Exact matrix completion via convex optimization
• Guaranteed Matrix Completion via Non-Convex Factorization
• Phase Retrieval via Wirtinger Flow: Theory and Algorithms
• Fast computation of low-rank matrix approximations
• A Simple SVD Algorithm for Finding Hidden Partitions
• Gradient Descent Only Converges to Minimizers: Non-Isolated Critical Points and Invariant Regions
• Symmetry, Saddle Points, and Global Optimization Landscape of Nonconvex Matrix Factorization
• The non-convex geometry of low-rank matrix optimization
• Recovering Low-Rank Matrices From Few Coefficients in Any Basis
• Matrix Completion From a Few Entries
• A Simpler Approach to Matrix Completion
• Restricted strong convexity and weighted matrix completion: Optimal bounds with noise
• Low-rank matrix completion using alternating minimization
• Regularized M-estimators with nonconvexity: Statistical and algorithmic theory for local optima
• Inequalities: theory of majorization and its applications
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item