Abstract
In this paper, we study a class of nonconvex and nonsmooth optimization problems, whose objective function can be split into two separable terms and one coupling term. Alternating proximal gradient methods combining with extrapolation are proposed to solve such problems. Under some assumptions, we prove that every cluster point of the sequence generated by our algorithms is a critical point. Furthermore, if the objective function satisfies Kurdyka–Łojasiewicz property, the generated sequence is globally convergent to a critical point. In order to make the algorithm more effective and flexible, we also use some strategies to update the extrapolation parameter and solve the problems with unknown Lipschitz constant. Numerical experiments demonstrate the effectiveness of our algorithms.
Similar content being viewed by others
References
Paatero, P., Tapper, U.: Positive matrix factorization: a nonnegative factor model with optimal utilization of error estimates of data values. Environmetrics 5, 111–126 (1994)
Lee, D.D., Seung, H.S.: Learning the parts of objects by nonnegative matrix factorization. Nature 401, 788–791 (1999)
Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: Understanding and evaluating blind deconvolution algorithms. In: Proceedings of Computer Vision and Patter Recognition (CVPR) (2009)
Zhang, X., Zhang, X., Li, X., Li, Z., Wang, S.: Classify social image by integrating multimodal content multimed. Tools Appl. 77, 7469–7485 (2017)
Bugeau, A., Ta, V.T., Papadakis, N.: Variational exemplar-based image colorization. IEEE Trans. Image Process. 23, 298–307 (2014)
Pierre, F., Aujol, J.F., Bugeau, A., Papadakis, N., Ta, V.T.: Luminance-chrominance model for image colorization. SIAM J. Imaging Sci. 8, 536–563 (2015)
Bertsekas, D.P.: Nolinear Programming. Athena Scientific, Belmont (1995)
Auslender, A.: Asymptotic properties of the Fenchel dual functional and applications to decomposition problems. J. Optim. Theory Appl. 73, 427–499 (1992)
Attouch, H., Redont, P., Soubeyran, A.: A new class of alternating proximal minimization algorithms with costs-to-move. SIAM J. Optim. 18, 1061–1081 (2007)
Attouch, H., Bolte, J., Redont, P., Soubeyran, A.: Proximal alternating minimization and projection methods for nonconvex problems: an approach based on the Kurdyka–Łojasiewicz inequality. Math. Oper. Res. 35, 438–457 (2010)
Xu, Y., Yin, W.: A block coordinate descent method for regularized multiconvex optimization with applications to nonnegative tensor factorization and completion. SIAM J. Imaging Sci. 6, 1758–1789 (2013)
Attouch, H., Bolte, J.: On the convergence of the proximal algorithm for nonsmooth functions involving analytic features. Math. Program. Ser. B 116, 5–16 (2009)
Bolte, J., Sabach, S., Teboulle, M.: Proximal alternating linearized minimization for nonconvex and nonsmooth problems. Math. Program. 146, 459–494 (2014)
Pock, T., Sabach, S.: Inertial proximal alternating linearized minimization (iPALM) for nonconvex and nonsmooth problems. SIAM J. Imaging Sci. 9, 1756–1787 (2016)
Gao, X., Cai, X., Han, D.: A Gauss-Seidel type inertial proximal alternating linearized minimization for a class of nonconvex optimization problems. J. Global Optim. 76, 863–887 (2020)
Nikolova, M., Tan, P.: Alternating structure-adapted proximal gradient descent for nonconvex nonsmooth block-regularized problems. SIAM J. Optim. 29, 2053–2078 (2019)
Tan, P., Pierre, F., Nikolova, M.: Inertial alternating generalized Forward-Backward splitting for image colorization. J. Math. Imaging Vis. 61, 672–690 (2019)
Rockafellar, R.T., Wets, J.B.: Variational Analysis. Springer, New York (1998)
Nesterov, Y.: Lectures on Convex Optimization. Springer, New York (2018)
Bolte, J., Daniilidis, A., Lewis, A.: The Lojasiewicz inequality for nonsmooth subanalytic functions with applications to subgradient dynamical systems. SIAM J. Optim. 17, 1205–1223 (2006)
Nesterov, Y.: A method of solving a convex programming problem with convergence rate \(O( \frac{1}{k^2 }\)). Sov. Math. Dokl. 27, 372–376 (1983)
Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imaging Sci. 2, 183–202 (2009)
Li, H., Lin, Z.: Accelerated proximal gradient methods for nonconvex programming. In: Advances in Neural Information Processing Systems, pp. 379–387 (2015)
Li, Q., Zhou, Y., Liang, Y., Varshney, P.K.: Convergence analysis of proximal gradient with momentum for nonconvex optimization. In: Proceedings of the 34th International Conference on Machine Learning, 2111-2119 (2017)
Wu, Z., Li, M.: General inertial proximal gradient method for a class of nonconvex nonsmooth optimization problems. Comput. Optim. Appl. 73, 129–158 (2019)
Gong, P., Zhang, C., Lu, Z., Huang, J., Ye, J.: A general iterative shrinkage and thresholding algorithm for nonconvex regularized optimization problems. In: International Conference on Leadership and Management, 37–45 (2013)
Barzilai, J., Borwein, J.M.: Two-point step size gradient methods. IMA J. Numer. Anal. 8, 141–148 (1988)
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. 137, 91–129 (2013)
Ban, G.Y., Karoui, N.E., Lim, A.E.B.: Machine learning and portfolio optimization. Manag. Sci. 64, 1136–1154 (2016)
Chen, X., Peng, J., Zhang, S.: Sparse solutions to random standard quadratic optimization problems. Math. Program. 141, 273–293 (2013)
Genkin, A., Lewis, D.D., Madigan, D.: Large-scale Bayesian logistic regression for text categorization. Technometrics 49, 291–304 (2007)
Shevade, S.K., Keerthi, S.S.: A simple and efficient algorithm for gene selection using sparse logistic regression. Bioinformatics 19, 2246–2253 (2003)
Fridman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. Ann. Stat. 28, 337–407 (2000)
Zhang, T.: Analysis of multi-stage convex relaxation for sparse regularization. J. Mach. Learn. Res. 11, 1081–1107 (2010)
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
The work is supported by Grant National Natural Science Foundation of China (NSFC) 11971238.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Yang, X., Xu, L. Some accelerated alternating proximal gradient algorithms for a class of nonconvex nonsmooth problems. J Glob Optim 87, 939–964 (2023). https://doi.org/10.1007/s10898-022-01214-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10898-022-01214-3