Proposal of Distance-weighted Exponential Natural Evolution Strategies   [NE] [ES]

by

Fukushima, N., Nagata, Y., Kobayashi, S. and Ono, I.

Literature search on Evolutionary ComputationBBase ©1999-2013, Rasmus K. Ursem
     Home · Search · Adv. search · Authors · Login · Add entries   Webmaster
Note to authors: Please submit your bibliography and contact information - online papers are more frequently cited.

Info: Proceedings of the 2011 IEEE Congress on Evolutionary Computation (Conference proceedings), 2011, p. 164-171
Keywords:Numerical optimization., Evolution strategies
Abstract:
This paper presents a new evolutionary algorithm [EA] for function optimization [FO] named the distance-weighted exponential natural evolution strategies [NE] [ES] (DX-NES). DX-NES remedies two problems of a conventional method, the exponential natural evolution strategies [NE] [ES] (xNES), that shows good performance when it does not need to move the distribution for sampling individuals down the slope to the optimal point. The first problem of xNES is that the search efficiency deteriorates while the distribution moves down the slope of an ill-scaled function because it degenerates before reaching the optimal point. The second problem is that the settings of learning rates [LR] are inappropriate because they do not taking account of some factors affecting the estimate accuracy of the natural gradient. We compared the performance of DX-NES with that of xNES and CMA-ES on typical benchmark functions and confirmed that DX-NES outperformed the xNES on all the benchmark functions and that DX-NES showed better performance than CMA-ES on the almost all functions except the k-tablet function.
Notes:
CEC2011 sponsored by the IEEE Computational Intelligence Society, and previously sponsored by the EPS and the IET.
Internet search:Search Google
Search Google Scholar
Search Citeseer using Google
Search Google for PDF
Search Google Scholar for PDF
Search Citeseer for PDF using Google

Review item:

Mark as doublet (will be reviewed)

Print entry



BibTex:
@InProceedings{Fukushima:2011:PoDENES,
  title     = {Proposal of Distance-weighted Exponential Natural Evolution Strategies},
  author    = {Nobusumi Fukushima and Yuichi Nagata and Shigenobu Kobayashi and Isao Ono},
  pages     = {164--171},
  booktitle = {Proceedings of the 2011 IEEE Congress on Evolutionary Computation},
  year      = {2011},
  editor = "Alice E. Smith",
  month     = {5-8 June},
  address   = {New Orleans, USA},
  organization ="IEEE Computational Intelligence Society",
  publisher = "IEEE Press",
  ISBN      = {0-7803-8515-2},
  keywords  = {Numerical optimization., Evolution strategies},
  abstract  = {
This paper presents a new evolutionary algorithm for function optimization
named the distance-weighted exponential natural evolution strategies (DX-NES).
DX-NES remedies two problems of a conventional method, the exponential natural
evolution strategies (xNES), that shows good performance when it does not need
to move the distribution for sampling individuals down the slope to the
optimal point. The first problem of xNES is that the search efficiency
deteriorates while the distribution moves down the slope of an ill-scaled
function because it degenerates before reaching the optimal point. The second
problem is that the settings of learning rates are inappropriate because they
do not taking account of some factors affecting the estimate accuracy of the
natural gradient. We compared the performance of DX-NES with that of xNES and
CMA-ES on typical benchmark functions and confirmed that DX-NES outperformed
the xNES on all the benchmark functions and that DX-NES showed better
performance than CMA-ES on the almost all functions except the k-tablet
function.
},
  notes =	{CEC2011 sponsored by the IEEE Computational Intelligence Society, and previously sponsored by the EPS and the IET. },
}