Why noise may be good: additive noise on the sharp ridge

This paper considers self-adaptive (mu/mu_I,lambda)-evolution strategies on the noisy sharp ridge. The evolution strategy (ES) is treated as a dynamical system using the so-called evolution equations to model the ES's behavior. The approach requires the determination of the one-generational expected changes of the state variables - the progress measures. For the analysis, the stationary state behavior of the ES on the sharp ridge is considered. Contrary to the usual perception of noise, it is shown that noise has a positive influence on the performance. An explanation for this astonishing behavior is given and conditions for the usefulness of noise in other fitness landscapes are discussed.

[1]  Dirk V. Arnold,et al.  Cumulative Step Length Adaptation on Ridge Functions , 2006, PPSN.

[2]  L. Darrell Whitley,et al.  Searching in the Presence of Noise , 1996, PPSN.

[3]  Hans-Paul Schwefel,et al.  Evolution and Optimum Seeking: The Sixth Generation , 1993 .

[4]  Hans-Georg Beyer,et al.  Local performance of the (1 + 1)-ES in a noisy environment , 2002, IEEE Trans. Evol. Comput..

[5]  Michael Herdy,et al.  Reproductive Isolation as Strategy Parameter in Hierarichally Organized Evolution Strategies , 1992, PPSN.

[6]  H. Beyer,et al.  Noisy Local Optimization with Evolution Strategies , 2002 .

[7]  Hans-Georg Beyer,et al.  Self-adaptation of evolution strategies under noisy fitness evaluations , 2006, Genetic Programming and Evolvable Machines.

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

[9]  Hans-Paul Schwefel,et al.  Evolution and optimum seeking , 1995, Sixth-generation computer technology series.

[10]  Thomas Bäck,et al.  Evolution strategies applied to perturbed objective functions , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[11]  Nikolaus Hansen,et al.  A Derandomized Approach to Self-Adaptation of Evolution Strategies , 1994, Evolutionary Computation.

[12]  Jürgen Branke,et al.  Evolutionary optimization in uncertain environments-a survey , 2005, IEEE Transactions on Evolutionary Computation.

[13]  Hans-Georg Beyer,et al.  Local Performance of the (μ/μ, μ)-ES in a Noisy Environment , 2000, FOGA.

[14]  L. Darrell Whitley,et al.  Searching for Balance: Understanding Self-adaptation on Ridge Functions , 2006, PPSN.

[15]  Dirk V. Arnold,et al.  Step Length Adaptation on Ridge Functions , 2008, Evolutionary Computation.

[16]  Hans-Paul Schwefel,et al.  Evolution strategies – A comprehensive introduction , 2002, Natural Computing.

[17]  Hans-Georg Beyer,et al.  Mutative self-adaptation on the sharp and parabolic ridge , 2007, FOGA'07.

[18]  Hans-Georg Beyer,et al.  A New Approach for Predicting the Final Outcome of Evolution Strategy Optimization Under Noise , 2005, Genetic Programming and Evolvable Machines.

[19]  L. Darrell Whitley,et al.  Ruffled by Ridges: How Evolutionary Algorithms Can Fail , 2004, GECCO.

[20]  B. Arnold,et al.  A first course in order statistics , 1994 .

[21]  Zbigniew Michalewicz,et al.  Evolutionary Computation 2 , 2000 .

[22]  B. Arnold,et al.  A first course in order statistics , 2008 .

[23]  Hans-Georg Beyer,et al.  On the performance of (1, Lambda)-evolution strategies for the ridge function class , 2001, IEEE Trans. Evol. Comput..

[24]  Hans-Georg Beyer,et al.  Toward a Theory of Evolution Strategies: Self-Adaptation , 1995, Evolutionary Computation.

[25]  Dirk V. Arnold,et al.  Noisy Optimization With Evolution Strategies , 2002, Genetic Algorithms and Evolutionary Computation.

[26]  Ingo Rechenberg,et al.  Evolutionsstrategie : Optimierung technischer Systeme nach Prinzipien der biologischen Evolution , 1973 .

[27]  Hans-Georg Beyer,et al.  On the performance of (1,l)-Evolution Strategies at the ridge function class , 2001 .

[28]  Hans-Georg Beyer,et al.  Evolution strategies with cumulative step length adaptation on the noisy parabolic ridge , 2008, Natural Computing.

[29]  Stuart Kauffman,et al.  Adaptive walks with noisy fitness measurements , 1995, Molecular Diversity.

[30]  W. Vent,et al.  Rechenberg, Ingo, Evolutionsstrategie — Optimierung technischer Systeme nach Prinzipien der biologischen Evolution. 170 S. mit 36 Abb. Frommann‐Holzboog‐Verlag. Stuttgart 1973. Broschiert , 1975 .