Abstract | ||
---|---|---|
In this paper we prove that for a variety of practical problems and representations, there is a free lunch for search algorithms that specialise in the task of finding functions or programs that solve problems, such as genetic programming. In other words, not all such algorithms are equally good under all possible performance measures. We focus in particular on the case where the objective is to discover functions that fit sets of data-points - a task that we will call symbolic regression. We show under what conditions there is a free lunch for symbolic regression, highlighting that these are extremely restrictive. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1145/1527125.1527148 | FOGA |
Keywords | Field | DocType |
program induction,possible performance measure,search algorithm,practical problem,genetic programming,free lunch,fit set,symbolic regression,no free lunch,theory | Mathematical optimization,Search algorithm,Computer science,No free lunch in search and optimization,Genetic programming,Artificial intelligence,Symbolic regression,Machine learning | Conference |
Citations | PageRank | References |
14 | 0.68 | 6 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Riccardo Poli | 1 | 2589 | 308.79 |
Mario Graff | 2 | 125 | 21.24 |
Nicholas Freitag McPhee | 3 | 404 | 32.94 |