Abstract
A hybrid global optimization algorithm is proposed aimed at the class of objective functions with properties typical of the problems of non-linear least squares regression. Three components of hybridization are considered: simplicial partition of the feasible region, indicating and excluding vicinities of the main local minimizers from global search, and computing the indicated local minima by means of an efficient local descent algorithm. The performance of the algorithm is tested using a collection of non-linear least squares problems evaluated by other authors as difficult global optimization problems.
Similar content being viewed by others
References
Bjórck A.: Numerical Methods for Least Squares Problems. SIAM, Philadelphia (1996)
Demidenko E.: Criteria for global minimum of sum of squares in nonlinear regression. Comput. Stat. Data Anal. 51(3), 1739–1753 (2006)
Dorsey R.E., Mayer W.J.: Genetic algorithms for estimation problems with multiple optima, nondifferentiability, and other irregular features. J. Bus. Econ. Stat. 13(1), 53–66 (1995)
Gasimov R.: Augmented lagrangian duality and nondifferentiable optimization methods in nonconvex programming. J. Glob. Optim. 24, 187–203 (2002)
Goffe W., Ferrier G., Rogers J.: Global optimization of statistical functions with simulated annealing. J. Econ. 60, 65–99 (1994)
Griffits J.D., Hunt J.G.: Vehicle headways in urban areas. Traffic Eng. Control 32, 458–462 (1991)
Hansen E.R.: Global Optimization Using Interval Analysis. Marcel Dekker, New York (1992)
Horst R., Pardalos P., Thoai N.: Introduction to Global Optimization. Kluwer, New York (1995)
Křivý I., Tvrdík J., Krepec R.: Stochastic algorithms in nonlinear regression. Comput. Stat. Data Anal. 33, 277–290 (2000)
Křivý I., Tvrdík J., Misik L.: Adaptive population-based search: application to estimation of nonlinear regression parameters. Comput. Stat. Data Anal. 52(2), 713–724 (2007)
Mathar R., Žilinskas A.: A class of test functions for global optimization. J. Glob. Optim. 5, 195–199 (1994)
Mishra, S.: Performance of differential evolution method in least squares fitting of some typical nonlinear curves. http://mpra.ub.uni-muenchen.de/4656/
Nelles O.: Nonlinear System Identification From Classical Approaches to Neural Networks and Fuzzy Models. Springer, New York (2001)
Paulavičius R., Žilinskas J., Grothey A.: Investigation of selection strategies in branch and bound algorithm with simplicial partitions and combination of Lipschitz bounds. Optim. Lett. 4(2), 173–183 (2010)
Pinter J.: Global Optimization in Action, Continuous and Lipshitz Optimization: Algorithms, Implementations and Applications. Kluwer, New York (1996)
Schittkowski K.: Data Fitting in Dynamical Systems. Kluwer, New York (2002)
Sergeyev Y.: An information global optimization algorithm with local tuning. SIAM J. Optim. 5(4), 858–870 (1995)
Sergeyev Y.: Efficient partitions of n-dimensional intervals in the framework of diagonal algorithms. J. Optim. Theory Appl. 124, 503–510 (2005)
Sergeyev Y., Kvasov D.: Global search based on efficient diagonal partitions and a set of Lipschitz costants. SIAM J. Optim. 16, 910–937 (2006)
Sergeyev Y., Pugliese P., Famularo D.: Index information algorithm with local tuning for solving multidimensional global optimization problems with multiextremal constraints. Math. Program. 96(3), 489–512 (2003)
Strongin R., Sergeyev Y.: Global Optimization with Non-convex Constraints: Sequential and Parallel Algorithms. Kluwer, New York (2000)
Törn A., Žilinskas A.: Global optimization. Lect. Notes Comput. Sci. 350, 1–255 (1989)
Tvrdík, J.: Global optimization, evolutionary algorithms and their application to computational statistics. http://albert.osu.cz/tvrdik/down/global_optimization.html
Velzquez L., Phillips G.N., Tapia R.A., Zhang Y.: Selective search for global optimization of zero or small residual least-squares problems: a numerical study. Comput. Optim. Appl. 20(3), 299–315 (1989)
Žilinskas A.: Optimization of one-dimensional multimodal functions, Algorithm 133. J. R. Stat. Soc. Ser. C 23, 367–385 (1978)
Žilinskas A., Baronas D.: Optimization-based evaluation of concentrations in modeling the biosensor-aided measurement. Informatica 22(4), 589–600 (2011)
Žilinskas A., Žilinskas J.: Global optimization based on a statistical model and simplicial partitioning. Comput. Math. Appl. 44(7), 957–967 (2002). doi:10.1016/S0898-1221(02)00206-7
Žilinskas A., Žilinskas J.: Interval arithmetic based optimization in nonlinear regression. Informatica 21(1), 149–158 (2010)
Žilinskas A., Žilinskas J.: P-algorithm based on a simplicial statistical model of multimodal functions. TOP 18(2), 396–412 (2010)
Žilinskas J.: Branch and bound with simplicial partitions for global optimization. Math. Model. Anal. 13(1), 145–159 (2008). doi:10.3846/1392-6292.2008.13.145-159
Žilinskas J., Bogle I.D.L.: Balanced random interval arithmetic in market model estimation. Eur. J. Oper. Res. 175(3), 1367–1378 (2006). doi:10.1016/j.ejor.2005.02.013
Zhou W., Chen X.: Global convergence of a new hybrid gauss-newton structured BFGS method for nonlinear least squares problems. SIAM J. Optim. 20(5), 2422–2441 (2010)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Žilinskas, A., Žilinskas, J. A hybrid global optimization algorithm for non-linear least squares regression. J Glob Optim 56, 265–277 (2013). https://doi.org/10.1007/s10898-011-9840-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10898-011-9840-9