A no-free-lunch framework for coevolution
Proceedings of the 10th annual conference on Genetic and evolutionary computation
Unbiased coevolutionary solution concepts
Proceedings of the tenth ACM SIGEVO workshop on Foundations of genetic algorithms
Monotonicity versus performance in co-optimization
Proceedings of the tenth ACM SIGEVO workshop on Foundations of genetic algorithms
Analysis of coevolution for worst-case optimization
Proceedings of the 11th Annual conference on Genetic and evolutionary computation
Free lunches in pareto coevolution
Proceedings of the 11th Annual conference on Genetic and evolutionary computation
A First Study on the Use of Coevolutionary Algorithms for Instance and Feature Selection
HAIS '09 Proceedings of the 4th International Conference on Hybrid Artificial Intelligence Systems
Conservation of information in search: measuring the cost of success
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Bernoulli's principle of insufficient reason and conservation of information in computer search
SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
Evolutionary synthesis of nand logic: dissecting a digital organism
SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
An architecture for adaptive algorithmic hybrids
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics - Special issue on game theory
IFS-CoCo in the landscape contest: description and results
ICPR'10 Proceedings of the 20th International conference on Recognizing patterns in signals, speech, images, and videos
International Journal of Bio-Inspired Computation
On the practicality of optimal output mechanisms for co-optimization algorithms
Proceedings of the 11th workshop proceedings on Foundations of genetic algorithms
Multi-operator based evolutionary algorithms for solving constrained optimization problems
Computers and Operations Research
HAIS'12 Proceedings of the 7th international conference on Hybrid Artificial Intelligent Systems - Volume Part II
Proceedings of the 14th annual conference companion on Genetic and evolutionary computation
Particle Swarm Optimization to Design Ideotypes for Sustainable Fruit Production Systems
International Journal of Swarm Intelligence Research
A framework for evolutionary algorithms based on Charles Sanders Peirce's evolutionary semiotics
Information Sciences: an International Journal
Adaptive Memetic Differential Evolution with Global and Local neighborhood-based mutation operators
Information Sciences: an International Journal
ACM Transactions on Intelligent Systems and Technology (TIST) - Survey papers, special sections on the semantic adaptive social web, intelligent systems for health informatics, regular papers
Hi-index | 0.00 |
Recent work on the foundational underpinnings of black-box optimization has begun to uncover a rich mathematical structure. In particular, it is now known that an inner product between the optimization algorithm and the distribution of optimization problems likely to be encountered fixes the distribution over likely performances in running that algorithm. One ramification of this is the "No Free Lunch" (NFL) theorems, which state that any two algorithms are equivalent when their performance is averaged across all possible problems. This highlights the need for exploiting problem-specific knowledge to achieve better than random performance. In this paper, we present a general framework covering most optimization scenarios. In addition to the optimization scenarios addressed in the NFL results, this framework covers multiarmed bandit problems and evolution of multiple coevolving players. As a particular instance of the latter, it covers "self-play" problems. In these problems, the set of players work together to produce a champion, who then engages one or more antagonists in a subsequent multiplayer game. In contrast to the traditional optimization case where the NFL results hold, we show that in self-play there are free lunches: in coevolution some algorithms have better performance than other algorithms, averaged across all possible problems. However, in the typical coevolutionary scenarios encountered in biology, where there is no champion, the NFL theorems still hold.