Local optimality for stationary points of group zero-norm regularized problems and equivalent surrogates

References

• Zhang H. T. The benefit of group sparsity. Ann Statist. 2010;38:1978–2004.
   Web of Science ®Google Scholar
• Meier L, van De Geer S, Bühlmann P. The group lasso for logistic regression. J R Statist Soc Ser B. 2008;70:53–71.
   Google Scholar
• Obozinski G, Taskar B, Jordan MI. Joint covariate selection for grouped classification. Stat Comput. 2010;20:231–252.
   Web of Science ®Google Scholar
• Yuan M, Lin Y. Model selection and estimation in regression with grouped variables. J R Statist Soc Ser B. 2006;68:49–67.
   Google Scholar
• Gong P, Ye J, Zhang C. Multi-stage multi-task feature learning. J Mach Learn Res. 2013;14:2979–3010.
   Web of Science ®Google Scholar
• Jenatton R, Audibert J, Bach F. Structured variable selection with sparsity-inducing norms. J Mach Learn Res. 2011;12:2777–2824.
   Web of Science ®Google Scholar
• Zhang J, Ghahramani Z, Yang Y. Flexible latent variable models for multi-task learning. Mach Learn. 2008;73:221–242.
   Web of Science ®Google Scholar
• Ahsen ME, Vidyasagar M. Error bounds for compressed sensing algorithms with group sparsity: a unified approach. Appl Comput Harmon Anal. 2017;43:212–232.
   Web of Science ®Google Scholar
• Duarte MF, Eldar YC. Structured compressed sensing: from theory to applications. IEEE Trans Signal Process. 2011;59:4053–4085.
   Web of Science ®Google Scholar
• Yuan XT, Liu X, Yan S. Visual classification with multitask joint sparse representation. IEEE Trans Image Process. 2012;21:4349–4360.
   PubMed Web of Science ®Google Scholar
• Eldar YC, Mishali M. Robust recovery of signals from a structured union of subspaces. IEEE Trans Inform Theory. 2009;55:5302–5316.
   Web of Science ®Google Scholar
• Stojnic M, Parvaresh F, Hassibi B. On the reconstruction of block-sparse signals with an optimal number of measurements. IEEE Trans Signal Process. 2009;57:3075–3085.
   Web of Science ®Google Scholar
• Degras D. Sparse group fused lasso for model segmentation: a hybrid approach. Adv Data Anal Classification. 2021;15:625–671.
   Web of Science ®Google Scholar
• Deng W, Yin WT, Zhang Y. Group sparse optimization by alternating direction method. In: Proceedings of SPIE the International Society for Optical Engineering; Vol. 8858. Published in SPIE Proceedings, 2013.
   Google Scholar
• Yang Y, Zou H. A fast unified algorithm for solving group-lasso penalize learning problems. Statist Comput. 2015;15:1129–1141.
   Google Scholar
• Beck A, Hallak N. Optimization problems involving group sparsity terms. Math Program. 2019;178:39–67.
   Web of Science ®Google Scholar
• Guo X, Zhang H, Wang Y, et al. Model selection and estimation in high dimensional regression models with group SCAD. Stat Probab Lett. 2015;103:86–92.
   Web of Science ®Google Scholar
• Hu Y, Li C, Meng K, et al. Group sparse optimization via lp,q regularization. J Mach Learn Res. 2017;18:1–52.
   Web of Science ®Google Scholar
• Ling Q, Wen ZW, Yin WT. Decentralized jointly sparse signal recovery by reweighted lq minimization. IEEE Trans Signal Process. 2013;61:1165–1170.
   Web of Science ®Google Scholar
• Chartrand R. Exact reconstruction of sparse signals via nonconvex minimization. IEEE Signal Process Lett. 2007;14:707–710.
   Web of Science ®Google Scholar
• Chen XJ, Xu FM, Ye YY. Lower bound theory of nonzero entries in solutions of ℓ2-ℓp minimization. SIAM J Sci Comput. 2010;32:2832–2852.
   Web of Science ®Google Scholar
• Bradley PS, Mangasarian OL. Feature selection via concave minimization and support vector machines. In: Proceeding of International Conference on Machine Learning ICML; 1998; Madison, Wisconsin, USA.
   Google Scholar
• Rinaldi F, Schoen F, Sciandrone M. Concave programming for minimizing the zero-norm over polyhedral sets. Comput Optim Appl. 2010;46:467–486.
   Web of Science ®Google Scholar
• Fan J, Li R. Variable selection via nonconcave penalized likelihood and its oracle properties. J Am Stat Assoc. 2001;9:1348–1360.
   Web of Science ®Google Scholar
• Zhang CH. Nearly unbiased variable selection underminimax concave penalty. Ann Statist. 2010;38:894–942.
   Web of Science ®Google Scholar
• Blumensath T, Davies ME. Iterative thresholding for sparse approximations. J Fourier Anal Appl. 2008;14:629–654.
   Web of Science ®Google Scholar
• Lu ZS. Iterative hard thresholding methods for ℓ0 regularized convex cone programming. Math Program. 2014;147:125–154.
   Web of Science ®Google Scholar
• Nikolova M. Description of the minimizers of least squares regularized with ℓ0-norm. Uniqueness of the global minimizer. SIAM J Imaging Sci. 2013;6:904–937.
   Web of Science ®Google Scholar
• Wu F, Bian W. Accelerated iterative hard thresholding algorithm for ℓ0 regularized regression problem. J Global Optim. 2020;76:819–840.
   Web of Science ®Google Scholar
• Liu YL, Bi SJ, Pan SH. Equivalent Lipschitz surrogates for zero-norm and rank optimization problems. J Global Optim. 2018;72:679–704.
   Web of Science ®Google Scholar
• Ye JJ, Ye XY. Necessary optimality conditions for optimization problems with variational inequality constraints. Math Oper Res. 1997;4:977–997.
   Google Scholar
• Aubin JP. Lipschitz behavior of solutions to convex minimization problems. Math Oper Res. 1984;9:87–111.
   Web of Science ®Google Scholar
• Robinson SM. Some continuity properties of polyhedral multifunctions. Math Program Study. 1981;14:206–214.
   Web of Science ®Google Scholar
• Rockafellar RT, Wets RJ-B. Variational analysis. New York (NY): Springer; 1998.
   Google Scholar
• Dontchev AL, Rockafellar RT. Implicit functions and solution mappings. New York (NY): LLC; 2009. (Springer monographs in mathematics).
   Google Scholar
• Henrion R, Outrata JV. Calmness of constraint systems with applications. Math Program. 2005;104:437–464.
   Web of Science ®Google Scholar
• Ioffe AD. Regular points of Lipschitz functions. Trans Am Math Soc. 1979;251:61–69.
   Web of Science ®Google Scholar
• Dontchev AL, Rockafellar RT. Regularity and conditioning of solution mappings in variational analysis. Set-Valued Anal. 2004;12:79–109.
   Google Scholar
• Bai K, Ye JJ, Zhang J. Directional quasi-/pseudo-normality as sufficient conditions for metric subregularity. SIAM J Optim. 2019;29:2625–2649.
   Web of Science ®Google Scholar
• Gfrerer H. First order and second order characterizations of metric subregularity and calmness of constraint set mappings. SIAM J Optim. 2011;21:1439–1474.
   Web of Science ®Google Scholar
• Ioffe AD, Outrata JV. On metric and calmness qualification conditions in subdifferential calculus. Set-Valued Anal. 2008;16:199–227.
   Google Scholar
• Mordukhovich BS. Variational analysis and generalized differentiation I. New York (NY): Springer; 2006.
   Google Scholar
• Bauschke HH, Borwein JM, Li W. Strong conical hull intersection property, bounded linear regularity, Jameson's property (G), and error bounds in convex optimization. Math Program. 1999;86:135–160.
   Web of Science ®Google Scholar
• Mohammadib A, Mordukhovich S, Aarabi ME. Parabolic regularity in geometric variational analysis. Trans Am Math Soc. 2021;374:1711–1763.
   Web of Science ®Google Scholar
• Bonnans JF, Shapiro A. Perturbation analysis of optimization problems. New York (NY): Springer; 2000.
   Google Scholar
• Mordukhovich BS. Stability theory for parametric generalized equations and variational inequalities via nonsmooth analysis. Trans Am Math Soc. 1994;343:609–656.
   Web of Science ®Google Scholar
• Qian YT, Pan SH, Liu YL. Calmness of partial perturbation to composite rank constraint systems and its applications, 2021 Oct 8. arXiv:2102.10373v2.
   Google Scholar
• Zhang DD, Pan SH, Bi SJ. A proximal MM method for zero-norm regularized PLQ composite optimization problems. arXiv:2001.06176v1.
   Google Scholar
• Bian W, Chen XJ. A smoothing proximal gradient algorithm for nonsmooth convex regression with cardinality penalty. SIAM J Numer Anal. 2020;58:858–883.
   Web of Science ®Google Scholar
• Rockafellar RT. Convex analysis. Princeton (NJ): Princeton University Press; 1970.
   Google Scholar