On genetic algorithms

@inproceedings{Baum1995OnGA,
  title={On genetic algorithms},
  author={Eric B. Baum and Dan Boneh and Charles Garrett},
  booktitle={COLT '95},
  year={1995}
}
We analyze the performance of a Genetic Type Algorithm we call Culling and a variety of other algorithms on a problem we refer to as ASP. Culling is near optimal for this problem, highly noise tolerant, and the best known a~~roach . . in some regimes. We show that the problem of learning the Ising perception is reducible to noisy ASP. These results provide an example of a rigorous analysis of GA’s and give insight into when and how C,A’s can beat competing methods. To analyze the genetic… 
Where Genetic Algorithms Excel
TLDR
It is shown that the problem of learning the Ising perceptron is reducible to a noisy version of ASP, and an algorithm is described the authors call Explicitly Parallel Search that succeeds.
Noise, sampling, and efficient genetic algorthms
As genetic algorithms (GA) move into industry, a thorough understanding of how GAs are affected by noise is becoming increasingly important. Noise affects a GA's population sizing requirements,
18 FITNESS LANDSCAPES AND PERFORMANCE OF METAHEURISTICS
TLDR
A statistical analysis of the structure of the search space of some planar, euclidian instances of the traveling salesman problem leads to a hybrid genetic algorithm that competes rather well with other local search heuristics for the TSP, notably Jünger's et al.
On the Workings of Genetic Algorithms: The Genoclique Fixing Hypothesis
TLDR
A new hypothesis about the workings of genetic algorithms is submitted and it is explained why this hypothesis is superior to the building block hypothesis, and the results of an experiment are presented in which the use of a simple mechanism called clamping dramatically improved the performance of an SGA with uniform crossover on large, randomly generated instances of the MAX 3-SAT problem.
EVOLUTIONARY ALGORITHMS : WHAT , WHEN , AND HOW ?
TLDR
The merits and demerits of GAs are highlighted and issues of implementation to practical problems are discussed and the user has to integrate problem specific information in the algorithm.
The Analysis of Evolutionary Algorithms—A Proof That Crossover Really Can Help
TLDR
It is proved that an evolutionary algorithm can produce enough diversity such that the use of crossover can speedup the expected optimization time from superpolynomial to a polynomial of small degree.
Genetic Algorithms and the O(n Ln N) Complexity on Selected Test Functions
TLDR
Any GA that features an elitist selection scheme, a broad mutation operator, and uses a mutation probability m p = 1=n, converges with an O(n ln n) complexity; it is not necessary to use a highly optimized genetic algorithms.
Special Applications and Techniques
TLDR
This chapter considers behavioral simulation for the iterated prisoners dilemma with an evolutionary algorithm and study evolutionary algorithms for multi-criteria optimization, especially in the presence of conflicting criteria.
An Efficient Genetic Algorithm for the p-Median Problem
TLDR
The coding effort and the computational effort required are minimal, making the algorithm a good choice for practical applications requiring quick solutions, or for upper-bound generation to speed up optimal algorithms.
Selection in the Presence of Noise
TLDR
Stochastic tournament selection is shown to show that the noise inherent in the optimization problem should be taken into account by the selection operator, and that one should not reduce noise further than necessary.
...
...

References

SHOWING 1-10 OF 24 REFERENCES
When will a Genetic Algorithm Outperform Hill Climbing
TLDR
An "idealized" genetic algorithm (IGA) is analyzed that is significantly faster than RMHC and that gives a lower bound for GA speed.
An Overview of Evolutionary Algorithms for Parameter Optimization
Three main streams of evolutionary algorithms (EAs), probabilistic optimization algorithms based on the model of natural evolution, are compared in this article: evolution strategies (ESs),
Genetic Algorithms in Search Optimization and Machine Learning
TLDR
This book brings together the computer techniques, mathematical tools, and research results that will enable both students and practitioners to apply genetic algorithms to problems in many fields.
Quadratic dynamical systems
TLDR
It is proved that convergence to the limit requires only polynomial time when the graph is a tree, which demonstrates that such systems, though nonlinear, are amenable to quantitative analysis.
The Probabilistic Method
TLDR
A particular set of problems - all dealing with “good” colorings of an underlying set of points relative to a given family of sets - is explored.
Rigorous Learning Curve Bounds from Statistical Mechanics
TLDR
A mathematically rigorous theory of learning curves that is based on ideas from statistical mechanics is introduced, which can often exhibit dramatic properties such as phase transitions, as well as power law asymptotics not explained by the VC theory.
On the average tractability of binary integer programming and the curious transition to perfect generalization in learning majority functions
TLDR
A very simple learning algorithm, dubbed Majority Rule, is shown to have very curious properties which relate to the average case tractability of the problem, and almost all instances of binary integer programming with Q(n log n) (or O(n/ log n)) tiequalities to be satisfied are tractable.
The Transition to Perfect Generalization in Perceptrons
TLDR
A rigorous proof is given that if at least n examples are drawn from the uniform distribution on {1, 1}, then the probability is 2(n) that there is any other such perceptron consistent with the examples, and that perfect generalization holds for as low as 1.5.
Adaptation in natural and artificial systems
TLDR
Names of founding work in the area of Adaptation and modiication, which aims to mimic biological optimization, and some (Non-GA) branches of AI.
...
...