A Simple Yet Efficient Evolution Strategy for Large-Scale Black-Box Optimization

We propose an evolution strategy algorithm using a sparse plus low rank model for large-scale optimization in this paper. We first develop a rank one evolution strategy using a single principal search direction. It is of linear complexity. Then we extend it to multiple search directions, and develop a rank- ${m}$ evolution strategy. We illustrate that the principal search direction accumulates the natural gradients with respect to the distribution mean, and acts as a momentum term. Further, we analyze the optimal low rank approximation to the covariance matrix, and experimentally show that the principal search direction can effectively learn the long valley of the function with predominant search direction. Then we investigate the effects of Hessian on the algorithm performance. We conduct experiments on a class of test problems and the CEC’2010 LSGO benchmarks. The experimental results validate the effectiveness of our proposed algorithms.

[1]  Anne Auger,et al.  Comparison-based natural gradient optimization in high dimension , 2014, GECCO.

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

[3]  Petros Koumoutsakos,et al.  Reducing the Time Complexity of the Derandomized Evolution Strategy with Covariance Matrix Adaptation (CMA-ES) , 2003, Evolutionary Computation.

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

[5]  Xiaodong Li,et al.  A Comparative Study of CMA-ES on Large Scale Global Optimisation , 2010, Australasian Conference on Artificial Intelligence.

[6]  Shun-ichi Amari,et al.  Natural Gradient Works Efficiently in Learning , 1998, Neural Computation.

[7]  Bernhard Sendhoff,et al.  Simplify Your Covariance Matrix Adaptation Evolution Strategy , 2017, IEEE Transactions on Evolutionary Computation.

[8]  Hans-Georg Beyer,et al.  Performance analysis of evolutionary optimization with cumulative step length adaptation , 2004, IEEE Transactions on Automatic Control.

[9]  Antonio LaTorre,et al.  Multiple Offspring Sampling in Large Scale Global Optimization , 2012, 2012 IEEE Congress on Evolutionary Computation.

[10]  Anne Auger,et al.  Impacts of invariance in search: When CMA-ES and PSO face ill-conditioned and non-separable problems , 2011, Appl. Soft Comput..

[11]  Xin Yao,et al.  Large scale evolutionary optimization using cooperative coevolution , 2008, Inf. Sci..

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

[13]  Tom Schaul,et al.  A linear time natural evolution strategy for non-separable functions , 2011, GECCO.

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

[15]  M. Brand,et al.  Fast low-rank modifications of the thin singular value decomposition , 2006 .

[16]  Peter Tiño,et al.  Scaling Up Estimation of Distribution Algorithms for Continuous Optimization , 2011, IEEE Transactions on Evolutionary Computation.

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

[18]  Kenneth A. De Jong,et al.  A Cooperative Coevolutionary Approach to Function Optimization , 1994, PPSN.

[19]  Ata Kabán,et al.  Toward Large-Scale Continuous EDA: A Random Matrix Theory Perspective , 2013, Evolutionary Computation.

[20]  Nikolaus Hansen,et al.  A restart CMA evolution strategy with increasing population size , 2005, 2005 IEEE Congress on Evolutionary Computation.

[21]  Anne Auger,et al.  A median success rule for non-elitist evolution strategies: study of feasibility , 2013, GECCO '13.

[22]  Qingfu Zhang,et al.  An efficient rank-1 update for Cholesky CMA-ES using auxiliary evolution path , 2017, 2017 IEEE Congress on Evolutionary Computation (CEC).

[23]  Nikolaus Hansen,et al.  The CMA Evolution Strategy: A Comparing Review , 2006, Towards a New Evolutionary Computation.

[24]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[25]  Shahryar Rahnamayan,et al.  Metaheuristics in large-scale global continues optimization: A survey , 2015, Inf. Sci..

[26]  Eugenius Kaszkurewicz,et al.  Steepest descent with momentum for quadratic functions is a version of the conjugate gradient method , 2004, Neural Networks.

[27]  Tom Schaul,et al.  High dimensions and heavy tails for natural evolution strategies , 2011, GECCO '11.

[28]  Francisco Herrera,et al.  MA-SW-Chains: Memetic algorithm based on local search chains for large scale continuous global optimization , 2010, IEEE Congress on Evolutionary Computation.

[29]  Christian Igel,et al.  A computational efficient covariance matrix update and a (1+1)-CMA for evolution strategies , 2006, GECCO.

[30]  Christian Igel,et al.  Efficient covariance matrix update for variable metric evolution strategies , 2009, Machine Learning.

[31]  Xiaodong Li,et al.  Benchmark Functions for the CEC'2010 Special Session and Competition on Large-Scale , 2009 .

[32]  Ilya Loshchilov,et al.  LM-CMA: An Alternative to L-BFGS for Large-Scale Black Box Optimization , 2015, Evolutionary Computation.

[33]  Oswin Krause,et al.  A More Efficient Rank-one Covariance Matrix Update for Evolution Strategies , 2015, FOGA.

[34]  Andreas Zell,et al.  Main vector adaptation: a CMA variant with linear time and space complexity , 2001 .

[35]  Yun Shang,et al.  A Note on the Extended Rosenbrock Function , 2006 .

[36]  Tom Schaul,et al.  Natural Evolution Strategies , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

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

[38]  Xiaodong Li,et al.  A Competitive Divide-and-Conquer Algorithm for Unconstrained Large-Scale Black-Box Optimization , 2016, ACM Trans. Math. Softw..

[39]  Hans-Georg Beyer,et al.  Convergence Analysis of Evolutionary Algorithms That Are Based on the Paradigm of Information Geometry , 2014, Evolutionary Computation.

[40]  Anne Auger,et al.  Information-Geometric Optimization Algorithms: A Unifying Picture via Invariance Principles , 2011, J. Mach. Learn. Res..

[41]  Bernhard Sendhoff,et al.  Covariance Matrix Adaptation Revisited - The CMSA Evolution Strategy - , 2008, PPSN.

[42]  Tom Schaul,et al.  Exponential natural evolution strategies , 2010, GECCO '10.

[43]  James N. Knight,et al.  Reducing the space-time complexity of the CMA-ES , 2007, GECCO '07.

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