Analysis of evolutionary algorithms on the one-dimensional spin glass with power-law interactions

This paper provides an in-depth empirical analysis of several hybrid evolutionary algorithms on the one-dimensional spin glass model with power-law interactions. The considered spin glass model provides a mechanism for tuning the effective range of interactions, what makes the problem interesting as an algorithm benchmark. As algorithms, the paper considers the genetic algorithm (GA) with twopoint and uniform crossover, and the hierarchical Bayesian optimization algorithm (hBOA). hBOA is shown to outperform both variants of GA, whereas GA with uniform crossover is shown to perform worst. The differences between the compared algorithms become more significant as the problem size grows and as the range of interactions decreases. Unlike for GA with uniform crossover, for hBOA and GA with twopoint crossover, instances with short-range interactions are shown to be easier. The paper also points out interesting avenues for future research.

[1]  Martin Pelikan,et al.  Scalable Optimization via Probabilistic Modeling: From Algorithms to Applications (Studies in Computational Intelligence) , 2006 .

[2]  David Maxwell Chickering,et al.  A Bayesian Approach to Learning Bayesian Networks with Local Structure , 1997, UAI.

[3]  Martin Pelikan,et al.  Finding ground states of Sherrington-Kirkpatrick spin glasses with hierarchical boa and genetic algorithms , 2008, GECCO '08.

[4]  Qingfu Zhang,et al.  On the convergence of a class of estimation of distribution algorithms , 2004, IEEE Transactions on Evolutionary Computation.

[5]  A. P. Young,et al.  Monte Carlo studies of the one-dimensional Ising spin glass with power-law interactions , 2003 .

[6]  Nir Friedman,et al.  Learning Bayesian Networks with Local Structure , 1996, UAI.

[7]  C. V. Hoyweghen.  Detecting spin-flip symmetry in optimization problems , 2001 .

[8]  Martin Pelikan,et al.  Hierarchical BOA, Cluster Exact Approximation, and Ising Spin Glasses , 2006, PPSN.

[9]  Kalyanmoy Deb,et al.  Genetic Algorithms, Noise, and the Sizing of Populations , 1992, Complex Syst..

[10]  David E. Goldberg,et al.  The gambler''s ruin problem , 1997 .

[11]  Heinz Mühlenbein,et al.  FDA -A Scalable Evolutionary Algorithm for the Optimization of Additively Decomposed Functions , 1999, Evolutionary Computation.

[12]  H. Katzgraber,et al.  Universality-class dependence of energy distributions in spin glasses , 2005, cond-mat/0506209.

[13]  Franz Rothlauf,et al.  Representations for genetic and evolutionary algorithms , 2002, Studies in Fuzziness and Soft Computing.

[14]  Pedro Larrañaga,et al.  Towards a New Evolutionary Computation - Advances in the Estimation of Distribution Algorithms , 2006, Towards a New Evolutionary Computation.

[15]  Qingfu Zhang,et al.  On stability of fixed points of limit models of univariate marginal distribution algorithm and factorized distribution algorithm , 2004, IEEE Transactions on Evolutionary Computation.

[16]  K. F. Pál,et al.  Hysteretic optimization for the Sherrington Kirkpatrick spin glass , 2006 .

[17]  Károly F. Pál,et al.  The ground state energy of the Edwards-Anderson Ising spin glass with a hybrid genetic algorithm , 1996 .

[18]  J. Wesley Barnes,et al.  The theory of elementary landscapes , 2003, Appl. Math. Lett..

[19]  David E. Goldberg,et al.  Population sizing for entropy-based model building in discrete estimation of distribution algorithms , 2007, GECCO '07.

[20]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[21]  Franz Rothlauf,et al.  Network Random KeysA Tree Representation Scheme for Genetic and Evolutionary Algorithms , 2002, Evolutionary Computation.

[22]  David E. Goldberg,et al.  Hierarchical BOA Solves Ising Spin Glasses and MAXSAT , 2003, GECCO.

[23]  P. Anderson,et al.  One-dimensional spin-glass model with long-range random interactions , 1983 .

[24]  Fisher,et al.  Equilibrium behavior of the spin-glass ordered phase. , 1988, Physical review. B, Condensed matter.

[25]  Jan Naudts,et al.  The Effect of Spin-Flip Symmetry on the Performance of the Simple GA , 1998, PPSN.

[26]  A. Hartmann.  Ground-state clusters of two-, three-, and four-dimensional +/-J Ising spin glasses. , 1999, Physical review. E, Statistical, nonlinear, and soft matter physics.

[27]  Bart Naudts,et al.  Epistasis as a Basic Concept in Formal Landscape Analysis , 1997, ICGA.

[28]  S. Boettcher.  Extremal optimization for Sherrington-Kirkpatrick spin glasses , 2004, cond-mat/0407130.

[29]  Ingo Wegener,et al.  The Ising Model on the Ring: Mutation Versus Recombination , 2004, GECCO.

[30]  F. Barahona.  On the computational complexity of Ising spin glass models , 1982 .

[31]  David E. Goldberg,et al.  A hierarchy machine: Learning to optimize from nature and humans , 2003, Complex..

[32]  David E. Goldberg,et al.  The Gambler's Ruin Problem, Genetic Algorithms, and the Sizing of Populations , 1999, Evolutionary Computation.

[33]  Franz Rothlauf,et al.  Evaluation-Relaxation Schemes for Genetic and Evolutionary Algorithms , 2004 .

[34]  Helmut G. Katzgraber,et al.  Spin glasses and algorithm benchmarks: A one-dimensional view , 2007, 0711.1532.

[35]  Heinz Mühlenbein,et al.  Predictive Models for the Breeder Genetic Algorithm I. Continuous Parameter Optimization , 1993, Evolutionary Computation.

[36]  David E. Goldberg,et al.  Scalability of the Bayesian optimization algorithm , 2002, Int. J. Approx. Reason..

[37]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[38]  David E. Goldberg,et al.  Genetic Algorithms and the Variance of Fitness , 1991, Complex Syst..

[39]  Shumeet Baluja,et al.  A Method for Integrating Genetic Search Based Function Optimization and Competitive Learning , 1994 .

[40]  J. A. Lozano,et al.  Towards a New Evolutionary Computation: Advances on Estimation of Distribution Algorithms (Studies in Fuzziness and Soft Computing) , 2006 .

[41]  H. Mühlenbein,et al.  From Recombination of Genes to the Estimation of Distributions I. Binary Parameters , 1996, PPSN.

[42]  David E. Goldberg,et al.  A Survey of Optimization by Building and Using Probabilistic Models , 2002, Comput. Optim. Appl..

[43]  Dan Boneh,et al.  On genetic algorithms , 1995, COLT '95.

[44]  D. Goldberg,et al.  Domino convergence, drift, and the temporal-salience structure of problems , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[45]  C. Reeves,et al.  Properties of fitness functions and search landscapes , 2001 .

[46]  J. A. Lozano,et al.  Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation , 2001 .

[47]  Martin Pelikan,et al.  Hierarchical Bayesian optimization algorithm: toward a new generation of evolutionary algorithms , 2010, SICE 2003 Annual Conference (IEEE Cat. No.03TH8734).

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

[49]  D. Goldberg,et al.  Escaping hierarchical traps with competent genetic algorithms , 2001 .

[50]  S. Kirkpatrick,et al.  Infinite-ranged models of spin-glasses , 1978 .

[51]  S. Kobe.  Ground-state energy and frustration of the Sherrington-Kirkpatrick model and related models , 2003, cond-mat/0311657.

[52]  S. Kobe,et al.  A recursive branch-and-bound algorithm for the exact ground state of Ising spin-glass models , 1984 .

[53]  P. Bosman,et al.  Continuous iterated density estimation evolutionary algorithms within the IDEA framework , 2000 .

[54]  Local field distributions in spin glasses , 2007, 0711.3934.

[55]  Georges R. Harik,et al.  Finding Multimodal Solutions Using Restricted Tournament Selection , 1995, ICGA.