(1+1) Genetic Programming With Functionally Complete Instruction Sets Can Evolve Boolean Conjunctions and Disjunctions with Arbitrarily Small Error - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Artificial Intelligence Année : 2023

(1+1) Genetic Programming With Functionally Complete Instruction Sets Can Evolve Boolean Conjunctions and Disjunctions with Arbitrarily Small Error

Andrei Lissovoi
  • Fonction : Auteur
  • PersonId : 1236807
Pietro Oliveto
  • Fonction : Auteur

Résumé

Recently it has been proven that simple GP systems can efficiently evolve a conjunction of n variables if they are equipped with the minimal required components. In this paper, we make a considerable step forward by analysing the behaviour and performance of a GP system for evolving a Boolean conjunction or disjunction of n variables using a complete function set that allows the expression of any Boolean function of up to n variables. First we rigorously prove that a GP system using the complete truth table to evaluate the program quality, and equipped with both the AND and OR operators and positive literals, evolves the exact target function in O(ℓn log 2 n) iterations in expectation, where ℓ ≥ n is a limit on the size of any accepted tree. Additionally, we show that when a polynomial sample of possible inputs is used to evaluate the solution quality, conjunctions or disjunctions with any polynomially small generalisation error can be evolved with probability 1−O(log 2 (n)/n). The latter result also holds if GP uses AND, OR and positive and negated literals, thus has the power to express any Boolean function of n distinct variables. To prove our results we introduce a super-multiplicative drift theorem that gives significantly stronger runtime bounds when the expected progress is only slightly super-linear in the distance from the optimum.
Fichier principal
Vignette du fichier
andorAIJ.pdf (398.62 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04027536 , version 1 (13-03-2023)

Identifiants

Citer

Benjamin Doerr, Andrei Lissovoi, Pietro Oliveto. (1+1) Genetic Programming With Functionally Complete Instruction Sets Can Evolve Boolean Conjunctions and Disjunctions with Arbitrarily Small Error. Artificial Intelligence, 2023, 319, pp.103906. ⟨10.1016/j.artint.2023.103906⟩. ⟨hal-04027536⟩
10 Consultations
44 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More