Quality gain analysis of the weighted recombination evolution strategy on general convex quadratic functions

Quality gain is the expected relative improvement of the function value in a single step of a search algorithm. Quality gain analysis reveals the dependencies of the quality gain on the parameters of a search algorithm, based on which one can derive the optimal values for the parameters. In this paper, we investigate evolution strategies with weighted recombination on general convex quadratic functions. We derive a bound for the quality gain and two limit expressions of the quality gain. From the limit expressions, we derive the optimal recombination weights and the optimal step-size, and find that the optimal recombination weights are independent of the Hessian of the objective function. Moreover, the dependencies of the optimal parameters on the dimension and the population size are revealed. Differently from previous works where the population size is implicitly assumed to be smaller than the dimension, our results cover the population size proportional to or greater than the dimension. Simulation results show the optimal parameters derived in the limit approximates the optimal values in non-asymptotic scenarios.

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

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

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

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

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

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

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

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

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

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

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

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

[13]  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.

[14]  Anne Auger,et al.  Quality Gain Analysis of the Weighted Recombination Evolution Strategy on General Convex Quadratic Functions , 2016, FOGA '17.

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

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

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

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

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

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

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

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

[23]  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 .

[24]  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.

[25]  Anne Auger,et al.  Convergence results for the (1, lambda)-SA-ES using the theory of phi-irreducible Markov chains , 2005, Theor. Comput. Sci..

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

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

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

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

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

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

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

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

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

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