Error bound of critical points and KL property of exponent for squared F-norm regularized factorization
arXiv:1911.04293
Abstract
This paper is concerned with the squared F(robenius)-norm regularized factorization form for noisy low-rank matrix recovery problems. Under a suitable assumption on the restricted condition number of the Hessian for the loss function, we derive an error bound to the true matrix for the non-strict critical points with rank not more than that of the true matrix. Then, for the squared F-norm regularized factorized least squares loss function, under the noisy and full sample setting we establish its KL property of exponent on its global minimizer set, and under the noisy and partial sample setting achieve this property for a class of critical points. These theoretical findings are also confirmed by solving the squared F-norm regularized factorization problem with an accelerated alternating minimization method.
References in corpus (10)
- Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
- Quantum state tomography via compressed sensing
- An overview of low-rank matrix recovery from incomplete observations
- Restricted strong convexity and weighted matrix completion: Optimal bounds with noise
- Guaranteed Matrix Completion via Non-convex Factorization
- Global Optimality of Local Search for Low Rank Matrix Recovery
- No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis
- Matrix Completion has No Spurious Local Minimum
- The Non-convex Geometry of Low-rank Matrix Optimization
- The Global Optimization Geometry of Low-Rank Matrix Optimization