Abstract
We consider a class of generalized DC (difference-of-convex functions) programming, which refers to the problem of minimizing the sum of two convex (possibly nonsmooth) functions minus one smooth convex part. To efficiently exploit the structure of the problem under consideration, in this paper, we shall introduce a unified Douglas–Rachford method in Hilbert space. As an interesting byproduct of the unified framework, we can easily show that our proposed algorithm is able to deal with convex composite optimization models. Due to the nonconvexity of DC programming, we prove that the proposed method is convergent to a critical point of the problem under some assumptions. Finally, we demonstrate numerically that our proposed algorithm performs better than the state-of-the-art DC algorithm and alternating direction method of multipliers (ADMM) for DC regularized sparse recovery problems.
Similar content being viewed by others
Notes
The Matlab codes can be downloaded from https://github.com/mingyan08/ProxL1-L2.
References
Alvarado, A., Scutari, G., Pang, J.: A new decomposition method for multiuser DC-programming and its applications. IEEE Trans. Signal Process. 62, 2984–2998 (2014)
Aragon Artacho, F., Borwein, J.: Global convergence of a non-convex Douglas–Rachford iteration. J. Glob. Optim. 57, 753–769 (2013)
Aragon Artacho, F., Borwein, J., Tam, M.: Global behavior of the Douglas–Rachford method for a nonconvex feasibility problem. J. Glob. Optim. 65, 309–327 (2016)
Aragon Artacho, F., Vuong, P.: The boosted difference of convex functions algorithm for nonsmooth functions. SIAM J. Optim. 30, 980–1006 (2020)
Bauschke, H., Combettes, P.: Convex Analysis and Monotone Operator Theory in Hilbert Spaces. Springer, New York (2011)
Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends Mach. Learn. 3, 1–122 (2010)
Candés, E., Romberg, J., Tao, T.: Stable signal recovery from incomplete and inaccurate measurements. Commun. Pure Appl. Math. 59, 1207–1223 (2006)
Carrizosa, E., Guerrero, V., Morales, J.: Visualizing data as objects by DC (difference of convex) optimization. Math. Program. Ser. B 169, 119–140 (2018)
Chen, Y., Chi, Y.: Harnessing structures in big data via guaranteed low rank matrix estimation: recent theory and fast algorithms via convex and nonconvex optimization. IEEE Signal Process. Mag. 35(4), 14–31 (2018)
Combettes, P., Pesquet, J.: Proximal splitting methods in signal processing. In: Bauschke, H., Burachik, R., Combettes, P., Elser, V., Luke, D., Wolkowicz, H. (eds.) Fixed-Point Algorithms for Inverse Problems in Science and Engineering. Springer Optimization and Its ApplicationsSpringer Optimization and Its Applications, vol. 49, pp. 185–212. Springer, New York (2011)
Dao, M., Tam, M.: A Lyapunov-type approach to convergence of the Douglas–Rachford algorithm for a nonconvex setting. J. Glob. Optim. 73, 83–112 (2019)
Domingos, P.: A few useful things to know about machine learning. Commun. ACM 55, 78–87 (2012)
Eckstein, J.: Splitting methods for monotone operators with applications to parallel optimization. Ph.D. thesis, Massachusetts Institute of Technology (1989)
Eckstein, J., Bertsekas, D.: On the Douglas–Rachford splitting method and the proximal point algorithm for maximal monotone operators. Math. Program. 55, 293–318 (1992)
Guo, K., Han, D.: A note on the Douglas–Rachford splitting method for optimization problems involving hypoconvex functions. J. Glob. Optim. 72, 431–441 (2018)
Guo, K., Han, D., Yuan, X.: Convergence analysis of Douglas–Rachford splitting method for “strongly+weakly” convex programming. SIAM J. Numer. Anal. 55, 1549–1577 (2017)
Han, D., He, H., Yang, H., Yuan, X.: A customized Douglas–Rachford splitting algorithm for separable convex minimization with linear constraints. Numer. Math. 127, 167–200 (2014)
Horst, R., Thoai, N.: DC programming: overview. J. Optim. Theory Appl. 103, 1–43 (1999)
Jain, P., Kar, P.: Non-convex optimization for machine learning. Found. Trends Mach. Learn. 10(3–4), 142–336 (2017)
Khabbazibasmenj, A., Roemer, F., Vorobyov, S., Haardt, M.: Sum-rate maximization in two-way AF MIMO relaying: polynomial time solutions to a class of DC programming problems. IEEE Trans. Signal Process. 60, 5478–5493 (2012)
Le Thi, H., Pham Dinh, T.: A continuous approach for the concave cost supply problem via DC programming and DCA. Discrete Appl. Math. 156, 325–338 (2008)
Le Thi, H., Pham Dinh, T.: Feature selection in machine learning: an exact penalty approach using a difference of convex function algorithm. Mach. Learn. 101, 163–186 (2015)
Le Thi, H., Pham Dinh, T.: DC programming and DCA: thirty years of developments. Math. Program. Ser. A 169, 5–68 (2018)
Le Thi, H., Tran, D.: Optimizing a multi-stage production/inventory system by DC programming based approaches. Comput. Optim. Appl. 57, 441–468 (2014)
Li, G.Y., Pong, T.K.: Douglas–Rachford splitting for nonconvex optimization with application to nonconvex feasibility problems. Math. Program. 159, 371–401 (2016)
Li, M., Wu, Z.M.: Convergence analysis of the generalized splitting methods for a class of nonconvex optimization problems. J. Optim. Theory Appl. 183, 535–565 (2019)
Liu, T., Pong, T.K., Takeda, A.: A refined convergence analysis of pDCAe with applications to simultaneous sparse recovery and outlier detection. Comput. Optim. Appl. 73, 69–100 (2019)
Lou, Y., Yan, M.: Fast l1–l2 minimization via a proximal operator. J. Sci. Comput. 74, 767–785 (2018)
Lou, Y., Zeng, T., Osher, S., Xin, J.: A weighted difference of anisotropic and isotropic total variation model for image processing. SIAM J. Imaging Sci. 8, 1798–1823 (2015)
Lu, Z., Zhou, Z.: Nonmonotone enhanced proximal DC algorithms for structured nonsmooth DC programming. SIAM J. Optim. 29, 2725–2752 (2019)
Lu, Z., Zhou, Z., Sun, Z.: Enhanced proximal DC algorithms with extrapolation for a class of structured nonsmooth DC minimization. Math. Program. Ser. B 176, 369–401 (2019)
Luke, D.R., Martins, A.: Convergence analysis of the relaxed Douglas–Rachford algorithm. SIAM J. Optim. 30, 542–584 (2020)
Marino, G., Xu, H.K.: Convergence of generalized proximal point algorithm. Commun. Pure Appl. Anal. 3, 791–808 (2004)
Miao, W., Pan, S., Sun, D.: A rank-corrected procedure for matrix completion with fixed basis coefficients. Math. Program. 159, 289–338 (2016)
Pham Dinh, T., Le Thi, H.: Convex analysis approach to DC programming: theory, algorithms and applications. Acta Math. Vietnamica 22, 289–355 (1997)
Pham Dinh, T., Souad, E.B.: Algorithms for solving a class of nonconvex optimization problems. Methods of subgradients. In: Hiriart-Urruty, J.B. (ed.) Fermat Days 85: Mathematics for Optimization. North-Holland Mathematics Studies, vol. 129, pp. 249–271. North-Holland, Amsterdam (1986)
Piot, B., Geist, M., Pietquin, O.: Difference of convex functions programming for reinforcement learning. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol. 27, pp. 2519–2527. Curran Associates, Red Hook (2017)
Sun, T., Yin, P., Cheng, L., Jiang, H.: Alternating direction method of multipliers with difference of convex functions. Adv. Comput. Math. 44, 723–744 (2018)
Ta, M., Le Thi, H., Boudjeloud-Assala, L.: Clustering data stream by a sub-window approach using DCA. In: Perner, P. (ed.) Machine Learning and Data Mining in Pattern Recognition, pp. 279–292. Springer, Berlin (2012)
Themelis, A., Patrinos, P.: Douglas–Rachford splitting and ADMM for nonconvex optimization tight convergence results. SIAM J. Optim. 30, 149–181 (2020)
Wen, B., Chen, X., Pong, T.K.: A proximal difference-of-conex algorithm with extrapolation. Comput. Optim. Appl. 69, 297–324 (2018)
Yin, P., Lou, Y., He, Q., Xin, J.: Minimization of \(\ell _{1-2}\) for compressed sensing. SIAM J. Sci. Comput. 37, A536–A563 (2015)
Zhang, F., Yang, Z., Chen, Y., Yang, J., Yang, G.: Matrix completion via capped nuclear norm. IET Image Process. 12, 959–966 (2018)
Acknowledgements
The authors are grateful to the anonymous referees for their close reading and valuable comments, which led to great improvements of the paper, especially for one referee bringing our attention to the relevant references [26, 27, 41]. H. He was supported in part by Zhejiang Provincial Natural Science Foundation of China at Grant No. LY20A010018 and National Natural Science Foundation of China (No. 11771113).
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.
Rights and permissions
About this article
Cite this article
Chuang, CS., He, H. & Zhang, Z. A unified Douglas–Rachford algorithm for generalized DC programming. J Glob Optim 82, 331–349 (2022). https://doi.org/10.1007/s10898-021-01079-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10898-021-01079-y