ABSTRACT
The family of natural evolution strategies (NES) offers a principled approach to real-valued evolutionary optimization. NES follows the natural gradient of the expected fitness on the parameters of its search distribution. While general in its formulation, previous research has focused on multivariate Gaussian search distributions. Here we exhibit problem classes for which other search distributions are more appropriate, and then derive corresponding NES-variants.
First, for separable distributions we obtain SNES, whose complexity is only O(d) instead of O(d3). We apply SNES to problems of previously unattainable dimensionality, recovering lowest-energy structures on the Lennard-Jones atom clusters, and obtaining state-of-the-art results on neuro-evolution benchmarks. Second, we develop a new, equivalent formulation based on invariances. This allows for generalizing NES to heavy-tailed distributions, even those with undefined variance, which aids in overcoming deceptive local optima.
- H.-G. Beyer and H.-P. Schwefel. Evolution strategies: A comprehensive introduction. Natural Computing, 1:3--52, 2002. Google ScholarDigital Library
- T. Glasmachers, T. Schaul, and J. Schmidhuber. A Natural Evolution Strategy for Multi-Objective Optimization. In Parallel Problem Solving from Nature (PPSN), 2010. Google ScholarDigital Library
- T. Glasmachers, T. Schaul, Y. Sun, D. Wierstra, and J. Schmidhuber. Exponential Natural Evolution Strategies. In Genetic and Evolutionary Computation Conference (GECCO), Portland, OR, 2010. Google ScholarDigital Library
- F. Gomez, J. Schmidhuber, and R. Miikkulainen. Accelerated Neural Evolution through Cooperatively Coevolved Synapses. Journal of Machine Learning Research, 2008. Google ScholarDigital Library
- N. Hansen. The CMA evolution strategy: a comparing review. In J. Lozano, P. Larranaga, I. Inza, and E. Bengoetxea, editors, Towards a new evolutionary computation. Advances on estimation of distribution algorithms, pages 75--102. Springer, 2006.Google Scholar
- N. Hansen and A. Auger. Real-parameter black-box optimization benchmarking 2010: Experimental setup, 2010.Google Scholar
- N. Hansen and S. Finck. Real-parameter black-box optimization benchmarking 2010: Noiseless functions definitions, 2010.Google Scholar
- N. Hansen and A. Ostermeier. Completely derandomized self-adaptation in evolution strategies. Evolutionary Computation, 9(2):159--195, 2001. Google ScholarDigital Library
- R. Ros and N. Hansen. A Simple Modification in CMA-ES Achieving Linear Time and Space Complexity. In R. et al., editor, Parallel Problem Solving from Nature, PPSN X, pages 296--305. Springer, 2008. Google ScholarDigital Library
- T. Schaul, J. Bayer, D. Wierstra, Y. Sun, M. Felder, F. Sehnke, T. Rückstieß, and J. Schmidhuber. PyBrain. Journal of Machine Learning Research, 11:743--746, 2010. Google ScholarDigital Library
- Y. Sun, D. Wierstra, T. Schaul, and J. Schmidhuber. Efficient Natural Evolution Strategies. In Genetic and Evolutionary Computation Conference (GECCO), 2009. Google ScholarDigital Library
- Y. Sun, D. Wierstra, T. Schaul, and J. Schmidhuber. Stochastic Search using the Natural Gradient. In International Conference on Machine Learning (ICML), 2009. Google ScholarDigital Library
- D. Wales and J. Doye. Global Optimization by Basin-Hopping and the Lowest Energy Structures of Lennard-Jones Clusters Containing up to 110 Atoms. The Journal of Physical Chemistry A, 101(28):8, 1998.Google Scholar
- D. Wierstra, T. Schaul, J. Peters, and J. Schmidhuber. Natural Evolution Strategies. In Proceedings of the Congress on Evolutionary Computation (CEC08), Hongkong. IEEE Press, 2008.Google ScholarCross Ref
Index Terms
- High dimensions and heavy tails for natural evolution strategies
Recommendations
Exponential natural evolution strategies
GECCO '10: Proceedings of the 12th annual conference on Genetic and evolutionary computationThe family of natural evolution strategies (NES) offers a principled approach to real-valued evolutionary optimization by following the natural gradient of the expected fitness. Like the well-known CMA-ES, the most competitive algorithm in the field, ...
Benchmarking exponential natural evolution strategies on the noiseless and noisy black-box optimization testbeds
GECCO '12: Proceedings of the 14th annual conference companion on Genetic and evolutionary computationNatural Evolution Strategies (NES) are a recent member of the class of real-valued optimization algorithms that are based on adapting search distributions. Exponential NES (xNES) are the most common instantiation of NES, and particularly appropriate for ...
Comparing natural evolution strategies to BIPOP-CMA-ES on noiseless and noisy black-box optimization testbeds
GECCO '12: Proceedings of the 14th annual conference companion on Genetic and evolutionary computationNatural Evolution Strategies (NES) are a recent member of the class of preal-valued optimization algorithms that are based on adapting search distributions. Exponential NES (xNES) are the most common instantiation of NES, and particularly appropriate ...
Comments