A new framework taking account of multi-funnel functions for Real-coded Genetic Algorithms

In this paper, we propose a new framework taking account of multi-funnel functions for Real-coded Genetic Algorithms (RCGAs). In the continuous function optimization, Evolutionary Algorithms (EAs) are one of the most effective optimization methods. However, most conventional EAs, such as RCGAs and CMA-ES, work efficiently on functions with big-valley landscape and they deteriorate on the multi-funnel functions. Innately Split Model (ISM) has been proposed as a framework of GAs for multi-funnel functions and outperforms conventional GAs on this kind of functions. However, ISM is considered to have two problems in terms of efficiency of the search and difficulty of parameter settings. Our framework repeats a search by RCGAs as ISM does and has two effective mechanisms to remedy the two problems of ISM. We conducted experiments on benchmark functions with multi-funnel and big-valley landscapes and our framework outperformed conventional EAs, Multi-start RCGA (MS-RCGA), Multi-start CMA-ES (MS-CMA-ES) and ISM, on the multi-funnel functions. Our framework achieved as good performance as MS-RCGA and MS-CMA-ES on the big-valley function where ISM significantly deteriorates.

[1]  Fred W. Glover,et al.  Tabu Search - Part I , 1989, INFORMS J. Comput..

[2]  Fred Glover,et al.  Tabu Search - Part II , 1989, INFORMS J. Comput..

[3]  Kenneth D. Boese,et al.  Cost Versus Distance In the Traveling Salesman Problem , 1995 .

[4]  Roberto Battiti,et al.  The continuous reactive tabu search: Blending combinatorial optimization and stochastic search for global optimization , 1996, Ann. Oper. Res..

[5]  J. Doye,et al.  THE DOUBLE-FUNNEL ENERGY LANDSCAPE OF THE 38-ATOM LENNARD-JONES CLUSTER , 1998, cond-mat/9808265.

[6]  Robert H. Leary,et al.  Global Optimization on Funneling Landscapes , 2000, J. Glob. Optim..

[7]  Shigenobu Kobayashi,et al.  GA Based on the UV-Structure Hypothesis and Its Application to JSP , 2000, PPSN.

[8]  Shigenobu Kobayashi,et al.  Multi-Parental Extension of the Unimodal Normal Distribution Crossover for Real-Coded Genetic Algorithms , 2000 .

[9]  Kalyanmoy Deb,et al.  A Computationally Efficient Evolutionary Algorithm for Real-Parameter Optimization , 2002, Evolutionary Computation.

[10]  Masao Fukushima,et al.  Tabu Search directed by direct search methods for nonlinear global optimization , 2006, Eur. J. Oper. Res..

[11]  Andrew M. Sutton,et al.  PSO and multi-funnel landscapes: how cooperation might limit exploration , 2006, GECCO.

[12]  Nikolaus Hansen,et al.  The CMA Evolution Strategy: A Comparing Review , 2006, Towards a New Evolutionary Computation.

[13]  Andrew M. Sutton,et al.  The Impact of Global Structure on Search , 2008, PPSN.

[14]  Isao Ono,et al.  Adaptation of expansion rate for real-coded crossovers , 2009, GECCO.

[15]  Christian L. Müller,et al.  A Tunable Real-world Multi-funnel Benchmark Problem for Evolutionary Optimization - And Why Parallel Island Models Might Remedy the Failure of CMA-ES on It , 2018, IJCCI.

[16]  Oliver Kramer,et al.  Surrogate Constraint Functions for CMA Evolution Strategies , 2009, KI.

[17]  淳 佐久間,et al.  適応的実数値交叉 AREX の提案と評価 , 2009 .

[18]  Jian-Ping Li,et al.  Random search with species conservation for multimodal functions , 2009, 2009 IEEE Congress on Evolutionary Computation.

[19]  Christian L. Müller,et al.  Particle Swarm CMA Evolution Strategy for the optimization of multi-funnel landscapes , 2009, 2009 IEEE Congress on Evolutionary Computation.

[20]  Isao Ono,et al.  A new real-coded genetic algorithm using the adaptive selection network for detecting multiple optima , 2009, 2009 IEEE Congress on Evolutionary Computation.

[21]  Isao Ono,et al.  Globally multimodal function optimization by Real-Coded Genetic Algorithms using traps , 2010, IEEE Congress on Evolutionary Computation.

[22]  Oliver Kramer,et al.  A Review of Constraint-Handling Techniques for Evolution Strategies , 2010, Appl. Comput. Intell. Soft Comput..