Abstract
Derivative-free optimization (DFO) is the mathematical study of the optimization algorithms that do not use derivatives. One branch of DFO focuses on model-based DFO methods, where an approximation of the objective function is used to guide the optimization algorithm. Proving convergence of such methods often applies an assumption that the approximations form fully linear models—an assumption that requires the true objective function to be smooth. However, some recent methods have loosened this assumption and instead worked with functions that are compositions of smooth functions with simple convex functions (the max-function or the \(\ell _1\) norm). In this paper, we examine the error bounds resulting from the composition of a convex lower semi-continuous function with a smooth vector-valued function when it is possible to provide fully linear models for each component of the vector-valued function. We derive error bounds for the resulting function values and subgradient vectors.
Similar content being viewed by others
References
Bauschke, H.H., Combettes, P.L.: Convex Analysis and Monotone Operator Theory in Hilbert Spaces. CMS Books in Mathematics/Ouvrages de Mathématiques de la SMC. Springer, New York (2011). With a foreword by Hédy Attouch
Bauschke, H.H., Hare, W.L., Moursi, W.M.: A derivative-free comirror algorithm for convex optimization. Optim. Methods Softw. 30(4), 706–726 (2015)
Bigdeli, K., Hare, W., Nutini, J., Tesfamariam, S.: Optimizing damper connectors for adjacent buildings. Optim. Eng. 17(1), 47–75 (2016)
Conn, A., Scheinberg, K., Toint, P.: On the convergence of derivative-free methods for unconstrained optimization. In: Approximation Theory and Optimization (Cambridge, 1996), pp. 83–108. Cambridge University Press, Cambridge (1997)
Conn, A.R., Scheinberg, K., Vicente, L.N.: Geometry of interpolation sets in derivative free optimization. Math. Program. 111(1–2, Ser. B), 141–172 (2008)
Conn, A.R., Scheinberg, K., Vicente, L.N.: Geometry of sample sets in derivative-free optimization: polynomial regression and underdetermined interpolation. IMA J. Numer. Anal. 28(4), 721–748 (2008)
Conn, A.R., Scheinberg, K., Vicente, L.N.: Global convergence of general derivative-free trust-region algorithms to first- and second-order critical points. SIAM J. Optim. 20(1), 387–415 (2009)
Conn, A.R., Scheinberg, K., Vicente, L.N.: Introduction to Derivative-Free Optimization, vol. 8 of MPS/SIAM Book Series on Optimization. SIAM (2009)
Custódio, A.L., Vicente, L.N.: Using sampling and simplex derivatives in pattern search methods. SIAM J. Optim. 18(2), 537–555 (2007)
Hare, W.L., Lucet, Y.: Derivative-free optimization via proximal point methods. J. Optim. Theory Appl. 160(1), 204–220 (2014)
Hare, W., Nutini, J.: A derivative-free approximate gradient sampling algorithm for finite minimax problems. Comput. Optim. Appl. 56(1), 1–38 (2013)
Larson, J., Menickelly, M., Wild, S.: Manifold sampling for \(l1\) nonconvex optimization. Technical report, Argonne National Laboratory (2015). http://www.mcs.anl.gov/papers/P5392-0915
Powell, M.J.D.: UOBYQA: unconstrained optimization by quadratic approximation. Math. Program. 92(3, Ser. B),555–582. ISMP 2000, Part 2 (Atlanta, GA) (2002)
Powell, M.J.D.: On trust region methods for unconstrained minimization without derivatives. Math. Program. 97(3),605–623 (2003). New trends in optimization and computational algorithms (NTOC 2001) (Kyoto)
Powell, M.J.D.: Developments of NEWUOA for minimization without derivatives. IMA J. Numer. Anal. 28(4), 649–664 (2008)
Regis, R.G.: The calculus of simplex gradients. Optim. Lett. 9(5), 845–865 (2015)
Rockafellar, R.T., Wets, R.J.-B.: Variational Analysis. Grundlehren der Mathematischen Wissenschaften [Fundamental Principles of Mathematical Sciences], vol. 317. Springer, Berlin (1998)
Wild, S.M., Shoemaker, C.: Global convergence of radial basis function trust region derivative-free algorithms. SIAM J. Optim. 21(3), 761–781 (2011)
Acknowledgements
This research was partially funded by the Natural Sciences and Engineering Research Council (NSERC) of Canada, Discover Grant #355571-2013.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hare, W. Compositions of convex functions and fully linear models. Optim Lett 11, 1217–1227 (2017). https://doi.org/10.1007/s11590-017-1117-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11590-017-1117-x