论文信息 - Benchmarking exponential natural evolution strategies on the noiseless and noisy black-box optimization testbeds

Benchmarking exponential natural evolution strategies on the noiseless and noisy black-box optimization testbeds

Natural 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 the BBOB 2012 benchmarks, given that many are non-separable, and their relatively small problem dimensions. This report provides the the most extensive empirical results on that algorithm to date, on both the noise-free and noisy BBOB testbeds.

Tom Schaul | T. Schaul

[1] N. Hansen,et al. Real-Parameter Black-Box Optimization Benchmarking: Experimental Setup , 2010 .

[2] Tom Schaul,et al. Natural evolution strategies converge on sphere functions , 2012, GECCO '12.

[3] Tom Schaul,et al. A Natural Evolution Strategy for Multi-objective Optimization , 2010, PPSN.

[4] Anne Auger,et al. Real-Parameter Black-Box Optimization Benchmarking 2009: Noiseless Functions Definitions , 2009 .

[5] Tom Schaul,et al. Studies in Continuous Black-box Optimization , 2011 .

[6] Isao Ono,et al. Proposal of distance-weighted exponential natural evolution strategies , 2011, 2011 IEEE Congress of Evolutionary Computation (CEC).

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

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

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

[10] Tom Schaul,et al. Stochastic search using the natural gradient , 2009, ICML '09.