Adaptive threshold parameter estimation with recursive differential grouping for problem decomposition

Problem decomposition plays an essential role in the success of cooperative co-evolution (CC), when used for solving large-scale optimization problems. The recently proposed recursive differential grouping (RDG) method has been shown to be very efficient, especially in terms of time complexity. However, it requires an appropriate parameter setting to estimate a threshold value in order to determine if two subsets of decision variables interact or not. Furthermore, using one global threshold value may be insufficient to identify variable interactions in components with different contribution to the fitness value. Inspired by the different grouping 2 (DG2) method, in this paper, we adaptively estimates a threshold value based on computational round-off errors for RDG. We derive an upper bound of the round-off errors, which is shown to be sufficient when identifying variable interactions across a wide range of large-scale benchmark problems. Comprehensive numerical experimental results showed that the proposed RDG2 method achieved higher decomposition accuracy than RDG and DG2. When embedded into a CC framework, it achieved statistically equal or significantly better solution quality than RDG and DG2, when used to solve the benchmark problems.

[1]  Ponnuthurai Nagaratnam Suganthan,et al.  Benchmark Functions for the CEC'2013 Special Session and Competition on Large-Scale Global Optimization , 2008 .

[2]  Zhenyu Yang,et al.  Large-Scale Global Optimization Using Cooperative Coevolution with Variable Interaction Learning , 2010, PPSN.

[3]  James Demmel,et al.  IEEE Standard for Floating-Point Arithmetic , 2008 .

[4]  Xiaodong Li,et al.  Benchmark Functions for the CEC'2010 Special Session and Competition on Large-Scale , 2009 .

[5]  Nikolaus Hansen,et al.  The CMA Evolution Strategy: A Tutorial , 2016, ArXiv.

[6]  Robert M. Corless,et al.  A Graduate Introduction to Numerical Methods , 2013 .

[7]  Maliha S. Nash,et al.  Handbook of Parametric and Nonparametric Statistical Procedures , 2001, Technometrics.

[8]  Daryl Essam,et al.  Decomposition-based evolutionary algorithm for large scale constrained problems , 2015, Inf. Sci..

[9]  Xiaodong Li,et al.  Cooperative Co-Evolution With Differential Grouping for Large Scale Optimization , 2014, IEEE Transactions on Evolutionary Computation.

[10]  Saman K. Halgamuge,et al.  On the Selection of Decomposition Methods for Large Scale Fully Non-separable Problems , 2015, GECCO.

[11]  Xiaodong Li,et al.  Cooperative Coevolution With Route Distance Grouping for Large-Scale Capacitated Arc Routing Problems , 2014, IEEE Transactions on Evolutionary Computation.

[12]  Haiyan Liu,et al.  Empirical study of effect of grouping strategies for large scale optimization , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[13]  Nicholas J. Higham,et al.  INVERSE PROBLEMS NEWSLETTER , 1991 .

[14]  Xiaodong Li,et al.  DG2: A Faster and More Accurate Differential Grouping for Large-Scale Black-Box Optimization , 2017, IEEE Transactions on Evolutionary Computation.

[15]  Ke Tang,et al.  Impact of problem decomposition on Cooperative Coevolution , 2013, 2013 IEEE Congress on Evolutionary Computation.

[16]  Xiaodong Li,et al.  Designing benchmark problems for large-scale continuous optimization , 2015, Inf. Sci..

[17]  Wei-neng Chen,et al.  Cooperation coevolution with fast interdependency identification for large scale optimization , 2017, Inf. Sci..

[18]  Saman K. Halgamuge,et al.  Quantifying Variable Interactions in Continuous Optimization Problems , 2017, IEEE Transactions on Evolutionary Computation.

[19]  Keith E. Mathias,et al.  In Parallel Problem Solving from Nature-PPSN III , 1994 .

[20]  Masaharu Munetomo,et al.  Linkage Identification by Nonlinearity Check for Real-Coded Genetic Algorithms , 2004, GECCO.

[21]  Kenneth A. De Jong,et al.  A Cooperative Coevolutionary Approach to Function Optimization , 1994, PPSN.

[22]  Xiaodong Li,et al.  A Competitive Divide-and-Conquer Algorithm for Unconstrained Large-Scale Black-Box Optimization , 2016, ACM Trans. Math. Softw..

[23]  Robert M. Corless,et al.  A Graduate Introduction to Numerical Methods: From the Viewpoint of Backward Error Analysis , 2013 .

[24]  Pat H. Sterbenz,et al.  Floating-point computation , 1973 .

[25]  Yuan Sun,et al.  Extended Differential Grouping for Large Scale Global Optimization with Direct and Indirect Variable Interactions , 2015, GECCO.

[26]  Andries Petrus Engelbrecht,et al.  A Cooperative approach to particle swarm optimization , 2004, IEEE Transactions on Evolutionary Computation.

[27]  Xin Yao,et al.  Large scale evolutionary optimization using cooperative coevolution , 2008, Inf. Sci..