Abstract
The paper proposes and justifies a new algorithm of the proximal Newton type to solve a broad class of nonsmooth composite convex optimization problems without strong convexity assumptions. Based on advanced notions and techniques of variational analysis, we establish implementable results on the global convergence of the proposed algorithm as well as its local convergence with superlinear and quadratic rates. For certain structured problems, the obtained local convergence conditions do not require the local Lipschitz continuity of the corresponding Hessian mappings that is a crucial assumption used in the literature to ensure a superlinear convergence of other algorithms of the proximal Newton type. The conducted numerical experiments of solving the \(l_1\) regularized logistic regression model illustrate the possibility of applying the proposed algorithm to deal with practically important problems.
Similar content being viewed by others
Notes
The code is downloaded from https://github.com/ZiruiZhou/IRPN.
References
Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imaging Sci. 2, 83–202 (2009)
Nesterov, Yu.: Lectures on Convex Optimization, 2nd edn. Springer, Cham, Switzerland (2018)
Schmidt, M., Roux, N., Bach, F.: Convergence rates of inexact proximal-gradient methods for convex optimization. In: Shawe-Taylor, J., et al. (eds.) Advances in Neural Information Processing Systems 24, pp. 1458–1466. Curran Associates, New York (2011)
Li, G., Pong, T.K.: Calculus of the exponent of Kurdyka-Łojasiewicz inequality and its applications to linear convergence of first-order methods. Found. Comput. Math. 18, 1199–1232 (2018)
Luo, Z.-Q., Tseng, P.: On the linear convergence of descent methods for convex essentially smooth minimization. SIAM J. Control. Optim. 30, 408–425 (1992)
Necoara, I., Nesterov, Yu., Glineur, F.: Linear convergence of first order methods for non-strongly convex optimization. Math. Progr. 175, 69–107 (2019)
Tseng, P.: Approximation accuracy, gradient methods, and error bound for structured convex optimization. Math. Progr. 125, 263–295 (2010)
Ye, J.J., Yuan, X., Zeng, S., Zhang, J.: Variational analysis perspective on linear convergence of some first order methods for nonsmooth convex optimization problems. Set-Valued Var. Anal. (2021). https://doi.org/10.1007/s11228-021-00591-3
Lee, J.D., Sun, Y., Saunders, M.A.: Proximal Newton-type methods for minimizing composite functions. SIAM J. Optim. 24, 1420–1443 (2014)
Fukushima, M., Mine, H.: A generalized proximal point algorithm for certain non-convex minimization problems. Int. J. Syst. Sci. 12, 989–1000 (1981)
Rockafellar, R.T.: Monotone operators and the proximal point algorithm. SIAM J. Control. Optim. 14, 877–898 (1976)
Facchinei, F., Pang, J.-S.: Finite-Dimesional Variational Inequalities and Complementarity Problems. Springer, New York (2003)
Izmailov, A.F., Solodov, M.V.: Newton-Type Methods for Optimization and Variational Problems. Springer, New York (2014)
Friedman, J., Hastie, T., Höfling, H., Tibshirani, R.: Pathwise coordinate optimization. Ann. Appl. Stat. 1, 302–332 (2007)
Yuan, G.-X., Ho, C.-H., Lin, C.-J.: An improved GLMNET for L1-regularized logistic regression. J. Mach. Learn. Res. 13, 1999–2030 (2012)
Hsieh, C., Dhillon, I.S., Ravikumar, P.K., Sustik, M.A.: Sparse inverse covariance matrix estimation using quadratic approximation. In: Shawe-Taylor, J., et al. (eds.) Advances in Neural Information Processing Systems 24, pp. 2330–2338. Curran Associates, New York (2011)
Oztoprak, F., Nocedal, J., Rennie, S., Olsen, P.A.: Newton-like methods for sparse inverse covariance estimation. In: Pereira, F., et al. (eds.) Advances in Neural Information Processing Systems 25, pp. 755–763. Curran Associates, New York (2012)
Sra, S., Nowozin, S., Wright, S.J. (eds.): Optimization for Machine Learning. MIT Press, Cambridge (2011)
Robinson, S.M.: Generalized equations and their solutions, Part II: applications to nonlinear programming. Math. Program. Stud. 19, 200–221 (1982)
Mordukhovich, B.S.: Variational Analysis and Applications. Springer, Cham, Switzerland (2018)
Dontchev, A.L., Rockafellar, R.T.: Implicit Functions and Solution Mappings: A View from Variational Analysis, 2nd edn. Springer, New York (2014)
Fischer, A.: Local behavior of an iterative framework for generalized equations with nonisolated solutions. Math. Progr. 94, 91–124 (2002)
Byrd, R.H., Nocedal, J., Oztoprak, F.: An inexact successive quadratic approximation method for L-1 regularized optimization. Math. Progr. 157, 375–396 (2016)
Lee, C., Wright, S.J.: Inexact successive quadratic approximation for regularized optimization. Comput. Optim. Appl. 72, 641–0674 (2019)
Scheinberg, K., Tang, X.: Practical inexact proximal quasi-Newton method with global complexity analysis. Math. Progr. 160, 495–529 (2016)
Yue, M.-C., Zhou, Z., So, A.M.-C.: A family of inexact SQA methods for non-smooth convex minimization with provable convergence guarantees based on the Luo-Tseng error bound property. Math. Progr. 174, 327–358 (2019)
Themelis, A., Stella, L., Patrinos, P.: Forward-backward envelope for the sum of two nonconvex functions: further properties and nonmonotone linesearch algorithms. SIAM J. Optim. 28, 2274–2303 (2018)
Mordukhovich, B.S., Nam, M.N.: An Easy Path to Convex Analysis. Morgan & Claypool Publishers, San Rafael, CA (2014)
Rockafellar, R.T., Wets, R.J.-B.: Variational Analysis. Springer, Berlin (1998)
Aragón Artacho, F.J., Geoffroy, M.H.: Characterization of metric regularity of subdifferentials. J. Convex Anal. 15, 365–380 (2008)
Aragón Artacho, F.J., Geoffroy, M.H.: Metric subregularity of the convex subdifferential in Banach spaces. J. Nonlin. Convex Anal. 15, 35–47 (2015)
Drusvyatskiy, D., Mordukhovich, B.S., Nghia, T.T.A.: Second-order growth, tilt stability, and metric regularity of the subdifferential. J. Convex Anal. 21, 1165–1192 (2014)
Gaydu, M., Geoffroy, M.H., Jean-Alexis, C.: Metric subregularity of order \(q\) and the solving of inclusions. Cent. Eur. J. Math. 9, 147–161 (2011)
Li, G., Mordukhovich, B.S.: Hölder metric subregularity with applications to proximal point method. SIAM J. Optim. 22, 1655–1684 (2012)
Zheng, X.Y., Ng, K.F.: Hölder stable minimizers, tilt stability sand Hölder metric regularity of subdifferentials. SIAM J. Optim. 120, 186–201 (2015)
Mordukhovich, B.S., Ouyang, W.: Higher-order metric subregularity and its applications. J. Global Optim. 63, 777–795 (2015)
Khanh, P.D., Mordukhovich, B.S., Phat, V.T.: A generalized Newton method for subgradient systems. arXiv:2009.10551v1 (2020)
Mordukhovich, B.S., Sarabi, M.E.: Generalized Newton algorithms for tilt-stable minimizers in nonsmooth optimization. arXiv:2004.02345 (2020)
Drusvyatskiy, D., Lewis, A.S.: Error bounds, quadratic growth, and linear convergence of proximal methods. Math. Oper. Res. 43, 919–948 (2018)
Beck, A.: First-Order Methods in Optimization. SIAM, Philadelphia (2017)
Chen, X., Fukushima, M.: Proximal quasi-Newton methods for nondifferentiable convex optimization. Math. Progr. 85, 313–334 (1999)
Dan, H., Yamashita, N., Fukushima, M.: Convergence properties of the inexact Levenberg-Marquardt method under local error bound conditions. Optim. Meth. Softw. 17, 605–626 (2002)
Chang, C.C., Lin, C.J.: LIBSVM?: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 27:1–27:27 (2011)
Acknowledgements
The authors are very grateful to two anonymous referees for their helpful suggestions and remarks that allowed us to significantly improve the original presentation. The alphabetical order of the authors indicates their equal contributions to the paper.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Boris S. Mordukhovich: Partly supported by the USA National Science Foundation under grants DMS-1512846 and DMS-1808978, by the USA Air Force Office of Scientific Research grant #15RT04, and by Australian Research Council Under Grant DP-190100555.
Xiaoming Yuan: Supported by the General Research Fund 12302318 from the Hong Kong Research Grants Council.
Shangzhi Zeng: Supported by the Pacific Institute for the Mathematical Sciences (PIMS)
Jin Zhang: Supported by National Science Foundation of China 11971220, by Shenzhen Science and Technology Program (No. RCYX20200714114700072), and by the Stable Support Plan Program of Shenzhen Natural Science Fund (No. 20200925152128002)
Rights and permissions
About this article
Cite this article
Mordukhovich, B.S., Yuan, X., Zeng, S. et al. A globally convergent proximal Newton-type method in nonsmooth convex optimization. Math. Program. 198, 899–936 (2023). https://doi.org/10.1007/s10107-022-01797-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10107-022-01797-5
Keywords
- Nonsmooth convex optimization
- Machine learning
- Proximal Newton methods
- Global and local convergence
- Metric subregularity