Natural Evolution Strategies

Details Natural Evolution Strategies Natural Evolution Strategies

2011-06-22

arxiv.org/abs/1106.4487v1

Statistics

Machine Learning

Scientific paper

This paper presents Natural Evolution Strategies (NES), a recent family of algorithms that constitute a more principled approach to black-box optimization than established evolutionary algorithms. NES maintains a parameterized distribution on the set of solution candidates, and the natural gradient is used to update the distribution's parameters in the direction of higher expected fitness. We introduce a collection of techniques that address issues of convergence, robustness, sample complexity, computational complexity and sensitivity to hyperparameters. This paper explores a number of implementations of the NES family, ranging from general-purpose multi-variate normal distributions to heavy-tailed and separable distributions tailored towards global optimization and search in high dimensional spaces, respectively. Experimental results show best published performance on various standard benchmarks, as well as competitive performance on others.

Affiliated with

Also associated with

No associations

Rating

Natural Evolution Strategies does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Natural Evolution Strategies, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Natural Evolution Strategies will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-206967