Abstract
A nonlinear stepsize control (NSC) framework has been proposed by Toint (Optim Methods Softw 28:82–95, 2013) for unconstrained optimization, generalizing several trust-region and regularization algorithms. More recently, worst-case complexity bounds to achieve approximate first-order optimality were proved by Grapiglia, Yuan and Yuan (Math Program 152:491–520, 2015) for the generic NSC framework. In this paper, improved complexity bounds for first-order optimality are obtained. Furthermore, complexity bounds for second-order optimality are also provided.
Similar content being viewed by others
References
Shultz, G.A., Schnabel, R.B., Byrd, R.H.: A family of trust-region-based algorithms for unconstrained minimization with strong global convergence properties. SIAM J. Numer. Anal. 22, 47–67 (1985)
Toint, PhL: Global convergence of a class of trust region methods for nonconvex minimization in Hilbert space. IMA J. Numer. Anal. 8, 231–252 (1988)
Toint, PhL: Nonlinear stepsize control, trust regions and regularizations for unconstrained optimization. Optim. Methods Softw. 28, 82–95 (2013)
Conn, A.R., Gould, N.I.M., Toint, PhL: Trust-Region Methods. SIAM, Philadelphia (2000)
Powell, M.J.D.: Convergence properties of a class of minimization algorithms. In: Mangasarian, O.L., Meyer, R.R., Robinson, S.M. (eds.) Nonlinear Programming 2. Academic Press, New York (1975)
Cartis, C., Gould, N.I.M., Toint, PhL: Adaptive cubic overestimation methods for unconstrained optimization. Part I: motivation, convergence and numerical results. Math. Program. 127, 245–295 (2011)
Cartis, C., Gould, N.I.M., Toint, PhL: Adaptive cubic regularisation methods for unconstrained optimization. Part II: worst-case function-and derivative-evaluation complexity. Math. Program. 130, 295–319 (2011)
Nesterov, Yu.: Modified Gauss–Newton scheme with worst-case guarantees for global performance. Optim. Methods Softw. 22, 469–483 (2007)
Bellavia, S., Cartis, C., Gould, N.I.M., Morini, B., Toint, PhL: Convergence of a regularized euclidean residual algorithm for nonlinear least-squares. SIAM J. Numer. Anal. 48, 1–29 (2010)
Fan, J., Yuan, Y.: A new trust region algorithm with trust region radius converging to zero. In: Li, D. (ed.) Proceeding of the 5th International Conference on Optimization: Techiniques and Applications, pp. 786–794. Hong Kong (2001)
Zhang, J., Wang, Y.: A new trust region method for nonlinear equations. Math. Methods Oper. Res. 58, 283–298 (2003)
Fan, J.: Convergence rate of the trust region method for nonlinear equations under local error bound condition. Comput. Optim. Appl. 34, 215–227 (2006)
Lu, X., Ni, Q.: A quasi-Newton trust-region method with a new conic model for the unconstrained optimization. Appl. Math. Comput. 204, 373–384 (2008)
Grapiglia, G.N., Yuan, J., Yuan, Y.: On the worst-case complexity of nonlinear stepsize control algorithms for convex unconstrained optimization. Optim. Methods Softw. 31, 591–604 (2016)
Grapiglia, G.N., Yuan, J., Yuan, Y.: On the convergence and worst-case complexity of trust-region and regularization methods for unconstrained optimization. Math. Program. 152, 491–520 (2015)
Powell, M.J.D.: On the global convergence of trust region algorithms for unconstrained minimization. Math. Program. 29, 297–303 (1984)
Cartis, C., Gould, N.I.M., Toint, P.L.: Worst-case evaluation complexity of regularization methods for smooth unconstrained optimization using Hölder continuous gradients. Technical Report NA-14-21, Mathematical Institute, University of Oxford (2014)
Cartis, C., Gould, N.I.M., Toint, PhL: Complexity bounds for second-order optimality in unconstrained optimization. J. Complex. 28, 93–108 (2012)
Nesterov, Yu.: Introductory Lectures on Convex Optimization. Applied Optimization. Kluwer, Dordrecht (2004)
Gratton, S., Sartenaer, A., Toint, Ph L.: Recursive trust-region methods for multiscale nonlinear optimization. SIAM J. Optim. 19, 414–444 (2008)
Cartis, C., Sampaio, PhR, Toint, PhL: Worst-case evaluation complexity of non-monotone gradient-related algorithms for unconstrained optimization. Optimization 64, 1349–1361 (2015)
Ueda, K., Yamashita, N.: On a global complexity bound of the Levenberg–Marquardt method. J. Optim. Theory Appl. 147, 443–453 (2010)
Nesterov, Yu., Polyak, B.T.: Cubic regularization of Newton method and its global performance. Math. Program. 108, 177–205 (2006)
Curtis, F.E., Robinson, D.P., Samadi, M.: A trust region algorithm with a worst-case iteration complexity of \(O(\epsilon ^{-3/2})\) for nonconvex optimization. Math. Program. doi:10.1007/s10107-016-1026-2
Martínez, J.M., Raydan, M.: Cubic-regularization counterpart of a variable-norm trust-region method for unconstrained minimization (2015). http://www.optimization-online.org/DB_FILE/2015/11/5203.pdf
Birgin, E.G., Gardenghi, J.L., Martínez, J.M., Toint, Ph.L.: Worst-case evaluation complexity for unconstrained nonlinear optimization using high-order regularized models. Technical Report naXys-05-2015, Namur Center for Complex Systems (naXys), University of Namur, Namur, Belgium (2015)
Acknowledgments
The authors are grateful to two anonymous referees for their valuable comments and suggestions to improve the paper. G.N. Grapiglia was supported by the Coordination for Improvement of Higher Education Personnel (CAPES), Brazil. J. Yuan was partially supported by the Coordination of the Improvement of Higher Education Personnel (CAPES) and by the National Council for Scientific and Technological Development (CNPq), Brazil. Y. Yuan was partially supported by the Natural Science Foundation of China (NSFC), China.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by Johannes O. Royset.
Rights and permissions
About this article
Cite this article
Grapiglia, G.N., Yuan, J. & Yuan, Yx. Nonlinear Stepsize Control Algorithms: Complexity Bounds for First- and Second-Order Optimality. J Optim Theory Appl 171, 980–997 (2016). https://doi.org/10.1007/s10957-016-1007-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10957-016-1007-x