Evolution strategies –A comprehensive introduction
Natural Computing: an international journal
Completely Derandomized Self-Adaptation in Evolution Strategies
Evolutionary Computation
Accelerated Neural Evolution through Cooperatively Coevolved Synapses
The Journal of Machine Learning Research
A Simple Modification in CMA-ES Achieving Linear Time and Space Complexity
Proceedings of the 10th international conference on Parallel Problem Solving from Nature: PPSN X
Stochastic search using the natural gradient
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Efficient natural evolution strategies
Proceedings of the 11th Annual conference on Genetic and evolutionary computation
The Journal of Machine Learning Research
Exponential natural evolution strategies
Proceedings of the 12th annual conference on Genetic and evolutionary computation
A natural evolution strategy for multi-objective optimization
PPSN'10 Proceedings of the 11th international conference on Parallel problem solving from nature: Part I
Sequential constant size compressors for reinforcement learning
AGI'11 Proceedings of the 4th international conference on Artificial general intelligence
Natural evolution strategies converge on sphere functions
Proceedings of the 14th annual conference on Genetic and evolutionary computation
Proceedings of the 14th annual conference companion on Genetic and evolutionary computation
Block diagonal natural evolution strategies
PPSN'12 Proceedings of the 12th international conference on Parallel Problem Solving from Nature - Volume Part II
A natural evolution strategy with asynchronous strategy updates
Proceedings of the 15th annual conference on Genetic and evolutionary computation
A linear time natural evolution strategy for non-separable functions
Proceedings of the 15th annual conference companion on Genetic and evolutionary computation
Hi-index | 0.00 |
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.