Asymptotic expansions for sums of nonidentically distributed Bernoulli random variables
Journal of Multivariate Analysis
Co-evolving parasites improve simulated evolution as an optimization procedure
CNLS '89 Proceedings of the ninth annual international conference of the Center for Nonlinear Studies on Self-organizing, Collective, and Cooperative Phenomena in Natural and Artificial Computing Networks on Emergent computation
On learning binary weights for majority functions
COLT '91 Proceedings of the fourth annual workshop on Computational learning theory
Adaptation in natural and artificial systems
Adaptation in natural and artificial systems
COLT '93 Proceedings of the sixth annual conference on Computational learning theory
Rigorous learning curve bounds from statistical mechanics
COLT '94 Proceedings of the seventh annual conference on Computational learning theory
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
An Introduction to Genetic Algorithms
An Introduction to Genetic Algorithms
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Numerical Optimization of Computer Models
Numerical Optimization of Computer Models
Properties of the Bucket Brigade
Proceedings of the 1st International Conference on Genetic Algorithms
Toward a theory of evolution strategies: On the benefits of sex---the (μ/μ, λ) theory
Evolutionary Computation
Proceedings of the 9th annual conference on Genetic and evolutionary computation
Are multiple runs of genetic algorithms better than one?
GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartI
| Hi-index | 0.00 |
We analyze the performance of a genetic algorithm (GA) we call Culling, and a variety of other algorithms, on a problem we refer to as the Additive Search Problem (ASP). We show that the problem of learning the Ising perceptron is reducible to a noisy version of ASP. Noisy ASP is the first problem we are aware of where a genetic-type algorithm bests all known competitors. We generalize ASP to k-ASP to study whether GAs will achieve "implicit parallelism" in a problem with many more schemata. GAs fail to achieve this implicit parallelism, but we describe an algorithm we call Explicitly Parallel Search that succeeds. We also compute the optimal culling point for selective breeding, which turns out to be independent of the fitness function or the population distribution. We also analyze a mean field theoretic algorithm performing similarly to Culling on many problems. These results provide insight into when and how GAs can beat competing methods.