See my reply here for an explanation of how little that conclusion of the paper means: http://news.ycombinator.com/item?id=4561418
In particular they tuned the GA but not he hill climber, so it's not clear that GAs win even on this artificially designed problem.
Re:Genetic Algorithms in CoffeeScript
by Turing_Machine on Sunday September 23, 2012 @02:58PM
(#4561717)
Wait a minute. First you were citing the paper's conclusion as supporting your position and now you're attacking the paper's conclusion?
I never cited the paper's conclusion as my position. What the paper shows is not what the paper concludes. The authors clearly didn't want to show that GAs are inferior, though inadvertently they certainly did. BTW, the authors of the paper conclude that further research is necessary to find cases where GAs outperform hill climbing.
I don't dispute that there are generally better optimization algorithms than GAs, but this paper does present an artificial case in a GA outperforms hill climbing.