Affine OneMax

A new class of test functions for black box optimization is introduced. Affine OneMax (AOM) functions are defined as compositions of OneMax and invertible affine maps on bit vectors. The black box complexity of the class is upper bounded by a polynomial of large degree in the dimension. Tunable complexity is achieved by expressing invertible linear maps as finite products of transvections. Finally, experimental results are given to illustrate the performance of search algorithms on AOM functions.

[1]  GUNAR E. LIEPINS,et al.  Representational issues in genetic optimization , 1990, J. Exp. Theor. Artif. Intell..

[2]  L. Darrell Whitley,et al.  Test Function Generators as Embedded Landscapes , 1998, FOGA.

[3]  William F. Punch,et al.  Fast and Efficient Black Box Optimization Using the Parameter-less Population Pyramid , 2015, Evolutionary Computation.

[4]  Laurent Saloff-Coste,et al.  Random Walks on Finite Groups , 2004 .

[5]  Rich Caruana,et al.  Removing the Genetics from the Standard Genetic Algorithm , 1995, ICML.

[6]  Anne Auger,et al.  COCO: Performance Assessment , 2016, ArXiv.

[7]  L. Darrell Whitley,et al.  Polynomial Time Summary Statistics for a Generalization of MAXSAT , 1999, GECCO.

[8]  Eyal Kushilevitz,et al.  Learning Decision Trees Using the Fourier Spectrum , 1993, SIAM J. Comput..

[9]  Carola Doerr,et al.  Complexity Theory for Discrete Black-Box Optimization Heuristics , 2018, Theory of Evolutionary Computation.

[10]  W. Hoeffding.  Probability Inequalities for sums of Bounded Random Variables , 1963 .

[11]  Sancho Salcedo-Sanz,et al.  On the application of linear transformations for genetic algorithms optimization , 2007, Int. J. Knowl. Based Intell. Eng. Syst..

[12]  M. Hildebrand.  Generating Random Elements in SLn (Fq) by Random Transvections , 1992 .

[13]  Arantxa Etxeverria.  The Origins of Order , 1993 .

[14]  David E. Goldberg,et al.  Genetic Algorithms and Walsh Functions: Part I, A Gentle Introduction , 1989, Complex Syst..

[15]  Kyomin Jung,et al.  Almost Tight Upper Bound for Finding Fourier Coefficients of Bounded Pseudo- Boolean Functions , 2008, COLT.

[16]  L. D. Whitley,et al.  The No Free Lunch and problem description length , 2001 .

[17]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[18]  David E. Goldberg,et al.  Hierarchical Bayesian Optimization Algorithm , 2006, Scalable Optimization via Probabilistic Modeling.

[19]  Thomas Jansen,et al.  UNIVERSITY OF DORTMUND REIHE COMPUTATIONAL INTELLIGENCE COLLABORATIVE RESEARCH CENTER 531 Design and Management of Complex Technical Processes and Systems by means of Computational Intelligence Methods Upper and Lower Bounds for Randomized Search Heuristics in Black-Box Optimization , 2004 .

[20]  ON TWO PROBLEMS OF INFORMATION THEORY , 2017 .

[21]  Nader H. Bshouty,et al.  Optimal Algorithms for the Coin Weighing Problem with a Spring Scale , 2009, COLT.

[22]  Heinz Mühlenbein,et al.  The Equation for Response to Selection and Its Use for Prediction , 1997, Evolutionary Computation.

[23]  Peter F. Stadler,et al.  Towards a theory of landscapes , 1995 .

[24]  Dirk Thierens,et al.  The Linkage Tree Genetic Algorithm , 2010, PPSN.

[25]  Paul A. Viola,et al.  MIMIC: Finding Optima by Estimating Probability Densities , 1996, NIPS.

[26]  Gunar E. Liepins,et al.  Polynomials, Basis Sets, and Deceptiveness in Genetic Algorithms , 1991, Complex Syst..

[27]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.