Genetic Programming Theory and Practice VIII

Volume 8 of the series Genetic and Evolutionary Computation pp 129-146


Age-Fitness Pareto Optimization

  • Michael SchmidtAffiliated withComputational Biology, Cornell University
  • , Hod LipsonAffiliated withSchool of Mechanical and Aerospace Engineering, Cornell UniversityComputing and Information Science, Cornell University

* Final gross prices may vary according to local VAT.

Get Access


We propose a multi-objective method, inspired by the Age Layered Population Structure algorithm, for avoiding premature convergence in evolutionary algorithms, and demonstrate a three-fold performance improvement over comparable methods. Previous research has shown that partitioning an evolving population into age groups can greatly improve the ability to identify global optima and avoid converging to local optima. Here, we propose that treating age as an explicit optimization criterion can increase performance even further, with fewer algorithm implementation parameters. The proposed method evolves a population on the two-dimensional Pareto front comprising (a) how long the genotype has been in the population (age); and (b) its performance (fitness). We compare this approach with previous approaches on the Symbolic Regression problem, sweeping the problem difficulty over a range of solution complexities and number of variables. Our results indicate that the multi-objective approach identifies the exact target solution more often than the age-layered population and standard population methods. The multi-objective method also performs better on higher complexity problems and higher dimensional datasets - finding global optima with less computational effort.


Symbolic Regression Age Fitness Multi-objective