A Linear Time Natural Evolution Strategy for Non-Separable Functions

Details A Linear Time Natural Evolution Strategy for Non-Separable Functions A Linear Time Natural Evolution Strategy for Non-Separable Functions

2011-06-10

arxiv.org/abs/1106.1998v2

Computer Science

Artificial Intelligence

Scientific paper

We present a novel Natural Evolution Strategy (NES) variant, the Rank-One NES (R1-NES), which uses a low rank approximation of the search distribution covariance matrix. The algorithm allows computation of the natural gradient with cost linear in the dimensionality of the parameter space, and excels in solving high-dimensional non-separable problems, including the best result to date on the Rosenbrock function (512 dimensions).

Affiliated with

Also associated with

No associations

Rating

A Linear Time Natural Evolution Strategy for Non-Separable Functions 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 A Linear Time Natural Evolution Strategy for Non-Separable Functions, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Linear Time Natural Evolution Strategy for Non-Separable Functions will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-320142