A Complete Characterization of the Robust Isolated Calmness of Nuclear Norm Regularized Convex Optimization Problems

In this paper, we provide a complete characterization on the robust isolated calmness of the Karush-Kuhn-Tucker (KKT) solution mapping for convex constrained optimization problems regularized by the nuclear norm function. This study is motivated by the recent work in [8], where the authors show that under the Robinson constraint qualification at a local optimal solution, the KKT solution mapping for a wide class of conic programming problem is robustly isolated calm if and only if both the second order sufficient condition (SOSC) and the strict Robinson constraint qualification (SRCQ) are satisfied. Based on the variational properties of the nuclear norm function and its conjugate, we establish the equivalence between the primal/dual SOSC and the dual/primal SRCQ. The derived results lead to several equivalent characterizations of the robust isolated calmness of the KKT solution mapping and add insights to the existing literature on the stability of the nuclear norm regularized convex optimization problems.

[1]  M. Yuan,et al.  Dimension reduction and coefficient estimation in multivariate linear regression , 2007 .

[2]  F. Clarke.  Optimization And Nonsmooth Analysis , 1983 .

[3]  Kim-Chuan Toh,et al.  Spectral operators of matrices , 2014, Mathematical Programming.

[4]  R. Tyrrell Rockafellar,et al.  Augmented Lagrangians and Applications of the Proximal Point Algorithm in Convex Programming , 1976, Math. Oper. Res..

[5]  Defeng Sun,et al.  Linear Rate Convergence of the Alternating Direction Method of Multipliers for Convex Composite Quadratic and Semi-Definite Programming , 2015, 1508.02134.

[6]  J. Frédéric Bonnans,et al.  Perturbation Analysis of Optimization Problems , 2000, Springer Series in Operations Research.

[7]  Kim-Chuan Toh,et al.  A Newton-CG Augmented Lagrangian Method for Semidefinite Programming , 2010, SIAM J. Optim..

[8]  Chao Ding.  Variational Analysis of the Ky Fan k-norm , 2016, 1601.07430.

[9]  Liwei Zhang,et al.  On the upper Lipschitz property of the KKT mapping for nonlinear semidefinite optimization , 2016, Oper. Res. Lett..

[10]  Ding Chao,et al.  AN INTRODUCTION TO A CLASS OF MATRIX OPTIMIZATION PROBLEMS , 2012 .

[11]  G. Alistair Watson,et al.  On matrix approximation problems with Ky Fank norms , 1993, Numerical Algorithms.

[12]  Pablo A. Parrilo,et al.  Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization , 2007, SIAM Rev..

[13]  G. Watson.  Characterization of the subdifferential of some matrix norms , 1992 .

[14]  Defeng Sun,et al.  Linear Rate Convergence of the Alternating Direction Method of Multipliers for Convex Composite Programming , 2017, Math. Oper. Res..

[15]  Paul Tseng,et al.  Trace Norm Regularization: Reformulations, Algorithms, and Multi-Task Learning , 2010, SIAM J. Optim..

[16]  Karl Löwner.  Über monotone Matrixfunktionen , 1934 .

[17]  Emmanuel J. Candès,et al.  Exact Matrix Completion via Convex Optimization , 2009, Found. Comput. Math..

[18]  Emmanuel J. Candès,et al.  The Power of Convex Relaxation: Near-Optimal Matrix Completion , 2009, IEEE Transactions on Information Theory.

[19]  Shaohua Pan,et al.  Locally upper Lipschitz of the perturbed KKT system of Ky Fan $k$-norm matrix conic optimization problems , 2015, 1509.00681.

[20]  Defeng Sun,et al.  Characterization of the Robust Isolated Calmness for a Class of Conic Programming Problems , 2017, SIAM J. Optim..