The Effects of Constant and Bit-Wise Neutrality on Problem Hardness, Fitness Distance Correlation and Phenotypic Mutation Rates

Kimura's neutral theory of evolution has inspired researchers from the evolutionary computation community to incorporate neutrality into evolutionary algorithms (EAs) in the hope that it can aid evolution. The effects of neutrality on evolutionary search have been considered in a number of studies, the results of which, however, have been highly contradictory. In this paper, we analyze the reasons for this and make an effort to shed some light on neutrality by addressing them. We consider two very simple forms of neutrality: constant neutrality-a neutral network of constant fitness, identically distributed in the whole search space-and bit-wise neutrality, where each phenotypic bit is obtained by transforming a group of genotypic bits via an encoding function. We study these forms of neutrality both theoretically and empirically (both for standard benchmark functions and a class of random MAX-SAT problems) to see how and why they influence the behavior and performance of a mutation-based EA. In particular, we analyze how the fitness distance correlation of landscapes changes under the effect of different neutral encodings and how phenotypic mutation rates vary as a function of genotypic mutation rates. Both help explain why the behavior of a mutation-based EA may change so radically as problem, form of neutrality, and mutation rate are varied.

[1]  Philippe Collard,et al.  Fitness Distance Correlation, as statistical measure of Genetic Algorithm difficulty, revisited , 1998, ECAI.

[2]  Julian Francis Miller,et al.  Finding Needles in Haystacks Is Not Hard with Neutrality , 2002, EuroGP.

[3]  Feller William,et al.  An Introduction To Probability Theory And Its Applications , 1950 .

[4]  M. Shackleton,et al.  An investigation of redundant genotype-phenotype mappings and their role in evolutionary search , 2000, Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512).

[5]  L. Dworsky.  An Introduction to Probability , 2008 .

[6]  M. Collins.  Finding needles in haystacks is harder with neutrality , 2005, GECCO '05.

[7]  Riccardo Poli,et al.  Some Steps Towards Understanding How Neutrality Affects Evolutionary Search , 2006, PPSN.

[8]  R. Shipman,et al.  Genetic Redundancy: Desirable or Problematic for Evolutionary Adaptation? , 1999, ICANNGA.

[9]  Julian Francis Miller,et al.  Cartesian genetic programming , 2010, GECCO.

[10]  Cláudio F. Lima,et al.  On the utility of the multimodal problem generator for assessing the performance of evolutionary algorithms , 2006, GECCO '06.

[11]  Elena Marchiori,et al.  Evolutionary Algorithms for the Satisfiability Problem , 2002, Evolutionary Computation.

[12]  Marc Ebner,et al.  How neutral networks influence evolvability , 2001, Complex..

[13]  Franz Rothlauf,et al.  Redundant Representations in Evolutionary Computation , 2003, Evolutionary Computation.

[14]  William Feller,et al.  An Introduction to Probability Theory and Its Applications , 1967 .

[15]  Anthony Brabazon,et al.  Defining locality in genetic programming to predict performance , 2010, IEEE Congress on Evolutionary Computation.

[16]  Riccardo Poli,et al.  Neutrality in evolutionary algorithms… What do we know? , 2011, Evol. Syst..

[17]  Leonardo Vanneschi,et al.  A Study of Fitness Distance Correlation as a Difficulty Measure in Genetic Programming , 2005, Evolutionary Computation.

[18]  M. Collins.  Finding needles in haystacks is harder with neutrality , 2006, Genetic Programming and Evolvable Machines.

[19]  Kenneth A. De Jong,et al.  Using Problem Generators to Explore the Effects of Epistasis , 1997, ICGA.

[20]  Hector J. Levesque,et al.  Hard and Easy Distributions of SAT Problems , 1992, AAAI.

[21]  L. Darrell Whitley,et al.  A Tractable Walsh Analysis of SAT and its Implications for Genetic Algorithms , 1998, AAAI/IAAI.

[22]  Anthony Brabazon,et al.  Towards an understanding of locality in genetic programming , 2010, GECCO '10.

[23]  Bart Selman,et al.  Local search strategies for satisfiability testing , 1993, Cliques, Coloring, and Satisfiability.

[24]  K. Holsinger.  The neutral theory of molecular evolution , 2004 .

[25]  Riccardo Poli,et al.  On the effects of bit-wise neutrality on fitness distance correlation, phenotypic mutation rates and problem hardness , 2007, FOGA'07.

[26]  Philippe Collard,et al.  Genetic Heuristic for Search Space Exploration , 1999, IJCAI.

[27]  Stephen A. Cook,et al.  The complexity of theorem-proving procedures , 1971, STOC.

[28]  Riccardo Poli,et al.  Generating SAT Local-Search Heuristics Using a GP Hyper-Heuristic Framework , 2007, Artificial Evolution.

[29]  Thomas Stützle,et al.  Exploiting Fitness Distance Correlation of Set Covering Problems , 2002, EvoWorkshops.

[30]  Donald W. Loveland,et al.  A machine program for theorem-proving , 2011, CACM.

[31]  P. Schuster,et al.  From sequences to shapes and back: a case study in RNA secondary structures , 1994, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[32]  Riccardo Poli,et al.  Fitness-proportional negative slope coefficient as a hardness measure for genetic algorithms , 2007, GECCO '07.

[33]  A. Wagner.  Robustness, evolvability, and neutrality , 2005, FEBS letters.

[34]  Hans-Georg Beyer,et al.  The Theory of Evolution Strategies , 2001, Natural Computing Series.

[35]  L. Vanneschi,et al.  Pros and Cons of Fitness Distance Correlation in Genetic Programming , 2003 .

[36]  Zbigniew Michalewicz,et al.  Parameter Control in Evolutionary Algorithms , 2007, Parameter Setting in Evolutionary Algorithms.

[37]  Kalyanmoy Deb,et al.  Ordering Genetic Algorithms and Deception , 1992, PPSN.

[38]  Leonardo Vanneschi,et al.  Fitness Distance Correlation And Problem Difficulty For Genetic Programming , 2002, GECCO.

[39]  Carlos M. Fonseca,et al.  Developing redundant binary representations for genetic search , 2005, 2005 IEEE Congress on Evolutionary Computation.

[40]  Frank Neumann,et al.  When to use bit-wise neutrality , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[41]  Sébastien Vérel,et al.  Deceptiveness and neutrality the ND family of fitness landscapes , 2006, GECCO.

[42]  N. Packard,et al.  Neutral Search Spaces for Artificial Evolution: A Lesson From Life , 2000 .

[43]  T. Jukes,et al.  The neutral theory of molecular evolution. , 2000, Genetics.

[44]  Zbigniew Michalewicz,et al.  Parameter control in evolutionary algorithms , 1999, IEEE Trans. Evol. Comput..

[45]  M. Kimura.  Evolutionary Rate at the Molecular Level , 1968, Nature.

[46]  N. Packard,et al.  Neutral search spaces for artificial evolution: a lesson from life , 2000 .

[47]  Riccardo Poli,et al.  The Effects of Constant Neutrality on Performance and Problem Hardness in GP , 2008, EuroGP.

[48]  Leonardo Vanneschi,et al.  Difficulty of Unimodal and Multimodal Landscapes in Genetic Programming , 2003, GECCO.

[49]  Tim Jones.  Evolutionary Algorithms, Fitness Landscapes and Search , 1995 .

[50]  Thomas Stützle,et al.  Local Search Algorithms for SAT: An Empirical Evaluation , 2000, Journal of Automated Reasoning.

[51]  David H. Wolpert,et al.  No free lunch theorems for optimization , 1997, IEEE Trans. Evol. Comput..

[52]  Kalyanmoy Deb,et al.  Massive Multimodality, Deception, and Genetic Algorithms , 1992, PPSN.

[53]  Victor J. Rayward-Smith,et al.  Fitness Distance Correlation and Ridge Functions , 1998, PPSN.

[54]  Marc Toussaint,et al.  Neutrality: a necessity for self-adaptation , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[55]  Marc Toussaint,et al.  On the Evolution of Phenotypic Exploration Distributions , 2002, FOGA.

[56]  M. Huynen,et al.  Neutral evolution of mutational robustness. , 1999, Proceedings of the National Academy of Sciences of the United States of America.

[57]  David E. Goldberg,et al.  Construction of high-order deceptive functions using low-order Walsh coefficients , 1992, Annals of Mathematics and Artificial Intelligence.

[58]  Riccardo Poli,et al.  An empirical investigation of how and why neutrality affects evolutionary search , 2006, GECCO '06.

[59]  Anthony Brabazon,et al.  Defining locality as a problem difficulty measure in genetic programming , 2011, Genetic Programming and Evolvable Machines.

[60]  Riccardo Poli,et al.  Foundations of Genetic Programming , 1999, Springer Berlin Heidelberg.

[61]  Terry Jones,et al.  Fitness Distance Correlation as a Measure of Problem Difficulty for Genetic Algorithms , 1995, ICGA.

[62]  Juan Julián Merelo Guervós,et al.  Proceedings of the 7th International Conference on Parallel Problem Solving from Nature , 1996 .

[63]  Riccardo Poli,et al.  A Field Guide to Genetic Programming , 2008 .

[64]  Yuri Pirola,et al.  A Comprehensive View of Fitness Landscapes with Neutrality and Fitness Clouds , 2007, EuroGP.

[65]  Marc Ebner,et al.  On neutral networks and evolvability , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[66]  Lee Altenberg,et al.  Fitness Distance Correlation Analysis: An Instructive Counterexample , 1997, ICGA.

[67]  Leonardo Vanneschi,et al.  Theory and practice for efficient genetic programming , 2004 .

[68]  P. Schuster,et al.  Generic properties of combinatory maps: neutral networks of RNA secondary structures. , 1997, Bulletin of mathematical biology.

[69]  Bart Selman,et al.  Noise Strategies for Improving Local Search , 1994, AAAI.

[70]  Hector J. Levesque,et al.  A New Method for Solving Hard Satisfiability Problems , 1992, AAAI.

[71]  Richard A. Watson,et al.  On the Utility of Redundant Encodings in Mutation-Based Evolutionary Search , 2002, PPSN.

[72]  Michael D. Vose,et al.  The simple genetic algorithm - foundations and theory , 1999, Complex adaptive systems.

[73]  Leonardo Vanneschi,et al.  Fitness Distance Correlation in Structural Mutation Genetic Programming , 2003, EuroGP.

[74]  Edgar Galván López.  An analysis of the effects of neutrality on problem hardness for evolutionary algorithms , 2009 .

[75]  J. Kennedy,et al.  Matching algorithms to problems: an experimental test of the particle swarm and some genetic algorithms on the multimodal problem generator , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).