Quality Gain Analysis of the Weighted Recombination Evolution Strategy on General Convex Quadratic Functions

We investigate evolution strategies with weighted recombination on general convex quadratic functions. We derive the asymptotic quality gain in the limit of the dimension to infinity, and derive the optimal recombination weights and the optimal step-size. This work is an extension of previous works where the asymptotic quality gain of evolution strategies with weighted recombination was derived on the infinite dimensional sphere function. Moreover, for a finite dimensional search space, we derive rigorous bounds for the quality gain on a general quadratic function. They reveal the dependency of the quality gain both in the eigenvalue distribution of the Hessian matrix and on the recombination weights. Taking the search space dimension to infinity, it turns out that the optimal recombination weights are independent of the Hessian matrix, i.e., the recombination weights optimal for the sphere function are optimal for convex quadratic functions.

[1]  Anne Auger,et al.  Log-Linear Convergence of the Scale-Invariant (µ/µw, lambda)-ES and Optimal µ for Intermediate Recombination for Large Population Sizes , 2010, PPSN.

[2]  Petros Koumoutsakos,et al.  A Method for Handling Uncertainty in Evolutionary Optimization With an Application to Feedback Control of Combustion , 2009, IEEE Transactions on Evolutionary Computation.

[3]  H.-G. Beyer,et al.  Mutate large, but inherit small ! On the analysis of rescaled mutations in (1, λ)-ES with noisy fitness data , 1998 .

[4]  References , 1971 .

[5]  A. Auger.  Analyse d’algorithmes stochastiques pour l’optimisation numérique bôıte-noire Analysis of Comparison-based Stochastic Continuous Black-Box Optimization Algorithms , 2016 .

[6]  Dirk V. Arnold,et al.  Weighted multirecombination evolution strategies , 2006, Theor. Comput. Sci..

[7]  Anne Auger,et al.  Reconsidering the progress rate theory for evolution strategies in finite dimensions , 2006, GECCO '06.

[8]  Youhei Akimoto,et al.  Online Model Selection for Restricted Covariance Matrix Adaptation , 2016, PPSN.

[9]  L. Devroye.  Non-Uniform Random Variate Generation , 1986 .

[10]  Raymond Ros,et al.  A Simple Modification in CMA-ES Achieving Linear Time and Space Complexity , 2008, PPSN.

[11]  H. Robbins.  A Remark on Stirling’s Formula , 1955 .

[12]  Ingo Rechenberg,et al.  Evolutionsstrategie '94 , 1994, Werkstatt Bionik und Evolutionstechnik.

[13]  Jens Jägersküpper,et al.  How the (1+1) ES using isotropic mutations minimizes positive definite quadratic forms , 2006, Theor. Comput. Sci..

[14]  Olivier Teytaud,et al.  General Lower Bounds for Evolutionary Algorithms , 2006, PPSN.

[15]  Anne Auger,et al.  Thèse d'habilitation à diriger des recherches "Analysis of Comparison-based Stochastic Continuous Black-Box Optimization Algorithms". (Thèse d'habilitation à diriger des recherches "Analysis of Comparison-based Stochastic Continuous Black-Box Optimization Algorithms") , 2016 .

[16]  Hans-Georg Beyer,et al.  Weighted recombination evolution strategy on a class of PDQF's , 2009, FOGA '09.

[17]  Ilya Loshchilov,et al.  A computationally efficient limited memory CMA-ES for large scale optimization , 2014, GECCO.

[18]  Nikolaus Hansen,et al.  Completely Derandomized Self-Adaptation in Evolution Strategies , 2001, Evolutionary Computation.

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

[20]  Nikolaus Hansen,et al.  Evaluating the CMA Evolution Strategy on Multimodal Test Functions , 2004, PPSN.

[21]  Anne Auger,et al.  Comparing results of 31 algorithms from the black-box optimization benchmarking BBOB-2009 , 2010, GECCO '10.

[22]  Anne Auger,et al.  Convergence of the Continuous Time Trajectories of Isotropic Evolution Strategies on Monotonic $\mathcal C^2$ -composite Functions , 2012, PPSN.

[23]  Anne Auger,et al.  Log-Linear Convergence and Optimal Bounds for the (1+1)-ES , 2007, Artificial Evolution.

[24]  Oswin Krause,et al.  Qualitative and Quantitative Assessment of Step Size Adaptation Rules , 2017, FOGA '17.

[25]  A. Dasgupta.  Asymptotic Theory of Statistics and Probability , 2008 .

[26]  Nikolaos V. Sahinidis,et al.  Derivative-free optimization: a review of algorithms and comparison of software implementations , 2013, J. Glob. Optim..

[27]  Hans-Georg Beyer,et al.  Towards a Theory of 'Evolution Strategies': Results for (1, +λ)-Strategies on (Nearly) Arbitrary Fitness Functions , 1994, PPSN.

[28]  Anne Auger,et al.  Mirrored sampling in evolution strategies with weighted recombination , 2011, GECCO '11.

[29]  Anne Auger,et al.  Linear Convergence of Comparison-based Step-size Adaptive Randomized Search via Stability of Markov Chains , 2013, SIAM J. Optim..

[30]  Nikolaus Hansen,et al.  Invariance, Self-Adaptation and Correlated Mutations and Evolution Strategies , 2000, PPSN.

[31]  Hans-Georg Beyer,et al.  The Dynamics of Cumulative Step Size Adaptation on the Ellipsoid Model , 2016, Evolutionary Computation.

[32]  Anne Auger,et al.  How to Assess Step-Size Adaptation Mechanisms in Randomised Search , 2014, PPSN.

[33]  Dirk V. Arnold,et al.  On the use of evolution strategies for optimising certain positive definite quadratic forms , 2007, GECCO '07.

[34]  Youhei Akimoto,et al.  Projection-Based Restricted Covariance Matrix Adaptation for High Dimension , 2016, GECCO.

[35]  Youhei Akimoto,et al.  Convergence of the Continuous Time Trajectories of Isotropic Evolution Strategies on Monotonic C^2-composite Functions , 2012 .

[36]  Anne Auger,et al.  Principled Design of Continuous Stochastic Search: From Theory to Practice , 2014, Theory and Principled Methods for the Design of Metaheuristics.

[37]  Youhei Akimoto,et al.  Benchmarking the novel CMA-ES restart strategy using the search history on the BBOB noiseless testbed , 2017, GECCO.

[38]  A. Auger.  Convergence results for the ( 1 , )-SA-ES using the theory of-irreducible Markov chains , 2005 .

[39]  P. Massart,et al.  Adaptive estimation of a quadratic functional by model selection , 2000 .

[40]  Hans-Georg Beyer,et al.  The Dynamics of Self-Adaptive Multirecombinant Evolution Strategies on the General Ellipsoid Model , 2014, IEEE Transactions on Evolutionary Computation.

[41]  Dirk V. Arnold,et al.  Optimal Weighted Recombination , 2005, FOGA.