Generalized Singular Value Thresholding

Abstract

This work studies the Generalized Singular Value Thresholding (GSVT) operator ${\text{Prox}}_g^{\sigma }(\cdot )$, \begin{equation*} {\text{Prox}}_{g}^{σ}(B)=\arg\min\limits_{X}\sum_{i=1}^{m}g(σ_{i}(X)) + \frac{1}{2}||X-B||_{F}^{2}, \end{equation*} associated with a nonconvex function $g$ defined on the singular values of $X$. We prove that GSVT can be obtained by performing the proximal operator of $g$ (denoted as ${\text{Prox}}_g(\cdot )$) on the singular values since ${\text{Prox}}_g(\cdot )$ is monotone when $g$ is lower bounded. If the nonconvex $g$ satisfies some conditions (many popular nonconvex surrogate functions, e.g., ${\ell }_p$-norm, $0<p<1$, of ${\ell }_0$-norm are special cases), a general solver to find ${\text{Prox}}_g(b)$ is proposed for any $b\ge 0$. GSVT greatly generalizes the known Singular Value Thresholding (SVT) which is a basic subroutine in many convex low rank minimization methods. We are able to solve the nonconvex low rank minimization problem by using GSVT in place of SVT.

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2015

References in corpus (3)

• Nearly unbiased variable selection under minimax concave penalty
• Generalized Nonconvex Nonsmooth Low-Rank Minimization
• Nonsmooth Analysis and Optimization

Cited by in corpus (5)

• Improved Sparse Low-Rank Matrix Estimation
• Iteratively Linearized Reweighted Alternating Direction Method of Multipliers for a Class of Nonconvex Problems
• Logistic principal component analysis via non-convex singular value thresholding
• Automated Spectral Kernel Learning
• Nonconvex Approach for Sparse and Low-Rank Constrained Models with Dual Momentum