Are Genetic Algorithms Function Optimizers?

By Kenneth De Jong. 1992

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition (2016, background): “…over other black-box optimization meth-ods such as surrogate models [3]—which require that the adversary has the training data and enough computational resources to train an eﬀective surrogate—and genetic algorithms [2]—which though similar to PSO are much less computationally eﬃcient [15, 34].”
Clustering-Based Adaptive Crossover and Mutation Probabilities for Genetic Algorithms (2007, methodology): “Among various evolutionary computation methods (ECM), genetic algorithms (GA), which have been applied to many optimization problems [7], [8], employ a random, yet directed, search for locating the global optimal solution.”
From evolutionary computation to the evolution of things (2015, background): “Nevertheless, it is important to understand that EAs are not optimizers 26 , but ‘approximizers’, and they are not optimal since we might not know whether a good evolved solution is the best possible.”
Evolutionary robotics: the Sussex approach (1997, background): “However, recently concerns have been voiced [12] to the e(cid:11)ect that GAs, when originally proposed by Holland [21], were intended as algorithms for complex adaptive systems, and their use for function optimisation is perhaps not best suited to their strengths.”
An Overview of Evolutionary Algorithms for Parameter Optimization (1993, background): “…should emphasize their parameter optimization properties or alternatively their more general adaptive capabilities is still ongoing (i.e., De Jong 1992), and it is clear that they benefit from a broad range of possible applications even in combinatorial optimization (due to the discrete…”
Derivative-free optimization: a review of algorithms and comparison of software implementations (2012, background): “Bethke [18] extended genetic algorithms to continuous problems by representing continuous variables by an approximate binary decomposition.”
Genetic Algorithms + Data Structures = Evolution Programs (1996, background): “This phenomenon is called deception [38], [154]: some building blocks (short, low-order schemata) can mislead genetic algorithm and cause its convergence to suboptimal points.”