Abstract. According to the No Free Lunch (NFL) theorems all blackbox algorithms perform equally well when compared over the entire set of optimization problems. An important proble...
Abstract—We consider two desired properties of learning algorithms: sparsity and algorithmic stability. Both properties are believed to lead to good generalization ability. We sh...
We present a statistical model of empirical optimization that admits the creation of algorithms with explicit and intuitively defined desiderata. Because No Free Lunch theorems di...
This paper investigates extensions of No Free Lunch (NFL) theorems to countably infinite and uncountable infinite domains. The original NFL due to Wolpert and Macready states th...
A number of recent studies introduced meta-evolutionary strategies and successfully used them for solving problems in genetic programming. While individual results indicate possib...