Share This Author
Probabilistic Model Building and Competent Genetic Programming
This paper describes probabilistic model building genetic programming (PM-BGP) developed based on the extended compact genetic algorithm (eCGA). Unlike traditional genetic programming, which use…
Linkage Learning via Probabilistic Modeling in the Extended Compact Genetic Algorithm (ECGA)
This chapter reveals the existence of GA-like algorithms that are potentially orders of magnitude faster and more accurate than the simple GA, and argues that these problems are equivalent.
Dependency Structure Matrix, Genetic Algorithms, and Effective Recombination
- Tian-Li Yu, D. Goldberg, K. Sastry, Cláudio F. Lima, M. Pelikán
- Computer ScienceEvolutionary Computation
- 1 December 2009
An automated dependency structure matrix clustering technique is developed and utilizes it to design a model-building genetic algorithm that learns and delivers the problem structure and helps researchers gain important insights through the explicitness of the procedure.
Combating user fatigue in iGAs: partial ordering, support vector machines, and synthetic fitness
- Xavier Llorà, K. Sastry, D. Goldberg, Abhimanyu Gupta, Lalitha Lakshmi
- Computer ScienceGECCO '05
- 25 June 2005
The proposed method combines partial ordering concepts, notion of non-domination from multiobjective optimization, and support vector machines to synthesize a fitness model based on user evaluation to combat user fatigue.
Multiobjective hBOA, clustering, and scalability
The algorithm mohBOA differs from the multiobjective variants of BOA and hBOA proposed in the past by including clustering in the objective space and allocating an approximately equally sized portion of the population to each cluster.
Scalability of the Bayesian optimization algorithm
Scalable Optimization via Probabilistic Modeling: From Algorithms to Applications (Studies in Computational Intelligence)
This work discusses linkage Learning via Probabilistic Modeling in the Extended Compact Genetic Algorithm and Hierarchical Bayesian Optimization Algorithm, as well as multiobjective Estimation of Distribution Algorithms.
Evaluation-Relaxation Schemes for Genetic and Evolutionary Algorithms
- K. Sastry, M. Pelikán, Prasanna Parthasarathy, Ravi Srivastava, Abhishek Sinha, Franz Rothlauf
- Computer Science
This thesis investigates fitness inheritance as an evaluation relaxation scheme, in which the fitness values of some individuals are inherited from their parents rather than through a costly evaluation function, thereby reducing the total function-evaluation cost.
Fitness Inheritance in the Bayesian Optimization Algorithm
The results indicate that fitness inheritance is a promising concept in BOA, because population-sizing requirements for building appropriate models of promising solutions lead to good fitness estimates even if only a small proportion of candidate solutions is evaluated using the actual fitness function.
Tournament Selection: Stable Fitness Pressure in XCS
This paper identifies problem properties in which performance of proportionate selection is impaired and tournament selection is introduced which makes XCS more parameter independent, noise independent, and more efficient in exploiting fitness guidance.