Regularized minimization problems with nonconvex, nonsmooth, even non-Lipschitz penalty functions have attracted much attention in recent years, owing to their wide applications in statistics, control, system identification and machine learning. In this paper, the non-Lipschitz ℓp (0 < p < 1) regularized matrix minimization problem is studied. A global necessary optimality condition for this non-Lipschitz optimization problem is firstly obtained, specifically, the global optimal solutions for the problem are fixed points of the so-called p-thresholding operator which is matrix-valued and set-valued. Then a fixed point iterative scheme for the non-Lipschitz model is proposed, and the convergence analysis is also addressed in detail. Moreover, some acceleration techniques are adopted to improve the performance of this algorithm. The effectiveness of the proposed p-thresholding fixed point continuation (p-FPC) algorithm is demonstrated by numerical experiments on randomly generated and real matrix completion problems.
ℓp regularized matrix minimization matrix completion problem p-thresholding operator global optimality condition fixed point continuation algorithm
90C06 90C26 90C46 65F22 65F30
This is a preview of subscription content, log in to check access.
This work was supported by National Natural Science Foundation of China (Grant Nos. 11401124 and 71271021), the Scientific Research Projects for the Introduced Talents of Guizhou University (Grant No. 201343) and the Key Program of Natural Science Foundation of China (Grant No. 11431002). The authors are thankful to the two anonymous referees for their valuable suggestions and comments that helped us to revise the paper into the present form.
Attouch H, Bolte J, Svaiter B F. Convergence of descent methods for semi-algebraic and tame problems: Proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods. Math Program, 2013, 137: 91–129MathSciNetCrossRefzbMATHGoogle Scholar
Fazel M, Hindi H, Boyd S. A rank minimization heuristic with application to minimum order system approximation. In: Proceedings of the American Control Conference. New York: IEEE, 2001, doi: 10.1109/ACC.2001.945730Google Scholar
Fazel M, Hindi H, Boyd S. Log-det heuristic for matrix rank minimization with applications to Hankel and Euclidean distance matrices. In: Proceedings of the American Control Conference. New York: IEEE, 2003, doi: 10.1109/AC-C.2003.1243393Google Scholar
Lai M-J, Xu Y, Yin W. Improved iteratively rewighted least squares for unconstrained smoothed lp minimization. SIAM J Numer Anal, 2013, 5: 927–957CrossRefzbMATHGoogle Scholar
Liu Z, Vandenberghe L. Interior-point method for nuclear norm approximation with application to system identification. SIAM J Matrix Anal Appl, 2009, 31: 1235–1256MathSciNetCrossRefzbMATHGoogle Scholar
Lu Y, Zhang L, Wu J. A smoothing majorization method for l22 -lpp matrix minimization. Optim Method Softw, 2014, 30: 1–24Google Scholar
Toh K C, Yun S. An accelerated proximal gradient algorithm for nuclear norm regularized least squares problems. Pac J Optim, 2010, 6: 615–640MathSciNetzbMATHGoogle Scholar
Wen Z, Yin W, Zhang Y. Solving a low-rank factorization model for matrix completion by a nonlinear successive over-relaxation algorithm. Math Program Comp, 2012, 4: 333–361MathSciNetCrossRefzbMATHGoogle Scholar
Xu Z, Chang X, Xu F, et al. L1/2 regularization: A thresholding representation theory and a fast solver. IEEE Trans Neural Network Learn Syst, 2012, 23: 1013–1027CrossRefGoogle Scholar
Zeng J, Lin S, Wang Y, et al. L1/2 regularization: Convergence of iterative half thresholding algorithm. IEEE Trans Signal Process, 2014, 62: 2317–2329MathSciNetCrossRefGoogle Scholar