Daniel R. Tauritz

Adaptive information filtering using evolutionary computation

Information Filtering is concerned with filtering data streams in such a way as to leave only pertinent data (information) to be perused. When the data streams are produced in a changing environment the filtering has to adapt too in order to remain eAective. Adaptive Information Filtering (AIF) is concerned with filtering in changing environments. The changes may occur both on the transmission side (the nature of the streams can change), and on the reception side (the interest of a user can change). Weighted trigram analysis is a quick and flexible technique for describing the contents of a document. A novel application of evolutionary computation is its use in Adaptive Information Filtering for optimizing various parameters, notably the weights associated with trigrams. The research described in this paper combines weighted trigram analysis, clustering, and a special two-pool evolutionary algorithm, to create an Adaptive Information Filtering system with such useful properties as domain independence, spelling error insensitivity, adaptability, and optimal use of user feedback while minimizing the amount of user feedback required to function properly. We designed a special evolutionary algorithm with a two-pool strategy for this changing environment. ” 2000 Elsevier Science Inc. All rights reserved.

Evolving black-box search algorithms employing genetic programming

Restricting the class of problems we want to perform well on allows Black Box Search Algorithms (BBSAs) specifically tailored to that class to significantly outperform more general purpose problem solvers. However, the fields that encompass BBSAs, including Evolutionary Computing, are mostly focused on improving algorithm performance over increasingly diversified problem classes. By definition, the payoff for designing a high quality general purpose solver is far larger in terms of the number of problems it can address, than a specialized BBSA. This paper introduces a novel approach to creating tailored BBSAs through automated design employing genetic programming. An experiment is reported which demonstrates its ability to create novel BBSAs which outperform established BBSAs including canonical evolutionary algorithms.

Coevolutionary automated software correction

This paper presents the Coevolutionary Automated Software Correction system, which addresses in an integral and fully automated manner the complete cycle of software artifact testing, error location, and correction phases. It employs a coevolutionary approach where software artifacts and test cases are evolved in tandem. The test cases evolve to better find flaws in the software artifacts and the software artifacts evolve to better behave to specification when exposed to the test cases, thus causing an evolutionary arms race. Experimental results are presented on the same test problem employed in the published results on the previous state-of-the-art automated software correction system.

Multi-objective coevolutionary automated software correction

For a given program, testing, locating the errors identified, and correcting those errors is a critical, yet expensive process. The field of Search Based Software Engineering (SBSE) addresses these phases by formulating them as search problems. The Coevolutionary Automated Software Correction (CASC) system targets the correction phase by coevolving test cases and programs at the source code level. This paper presents the latest version of the CASC system featuring multi-objective optimization and an enhanced representation language. Results are presented demonstrating CASCs ability to successfully correct five seeded bugs in two non-trivial programs from the Siemens test suite. Additionally, evidence is provided substantiating the hypothesis that multi-objective optimization is beneficial to SBSE.

Self-configuring crossover

Crossover is a core genetic operator in many evolutionary algorithms (EAs). The performance of such EAs on a given problem is dependent on properly configuring crossover. A small set of common crossover operators is used in the vast majority of EAs, typically fixed for the entire evolutionary run. Selecting which crossover operator to use and tuning its associated parameters to obtain acceptable performance on a specific problem often is a time consuming manual process. Even then a custom crossover operator may be required to achieve optimal performance. Finally, the best crossover configuration may be dependent on the state of the evolutionary run. This paper introduces the Self-Configuring Crossover operator encoded with linear genetic programming which addresses these shortcomings while relieving the user from the burden of crossover configuration. To demonstrate its general applicability, the novel crossover operator was applied without any problem specific tuning. Results are presented showing it to outperform the traditional crossover operators arithmetic crossover, uniform crossover, and n-point crossover on the Rosenbrock, Rastrigin, Offset Rastrigin, DTrap, and NK Landscapes benchmark problems.

Co-optimization algorithms

While coevolution has many parallels to natural evolution, methods other than those based on evolutionary principles may be used in the interactive fitness setting. In this paper we present a generalization of coevolution to co-optimization which allows arbitrary black-box function optimization techniques to be used in a coevolutionary like manner. We find that the co-optimization versions of gradient ascent and simulated annealing are capable of outperforming the canonical coevolutionary algorithm. We also hypothesize that techniques which employ non-population based selection mechanisms are less sensitive to disengagement.

A no-free-lunch framework for coevolution

The No-Free-Lunch theorem is a fundamental result in the field of black-box function optimization. Recent work has shown that coevolution can exhibit free lunches. The question as to which classes of coevolution exhibit free lunches is still open. In this paper we present a novel framework for analyzing No-Free-Lunch like results for classes of coevolutionary algorithms. Our framework has the advantage of analyzing No-Free-Lunch like inquiries in terms of solution concepts and isomorphisms on the weak preference relation on solution configurations. This allows coevolutionary algorithms to be naturally classified by the type of solution they seek. Using the weak preference relation also permits us to present a simpler definition of performance metrics than that used in previous coevolutionary No-Free-Lunch work, more akin to the definition used in the original No-Free-Lunch theorem. The framework presented in this paper can be viewed as the combination of the ideas and definitions from two separate theoretical frameworks for analyzing search algorithms and coevolution consistent with the terminology of both. We also present a new instance of free lunches in coevolution which demonstrates the applicability of our framework to analyzing coevolutionary algorithms based upon the solution concept which they implement.

Linkage tree genetic algorithms: variants and analysis

Discovering and exploiting the linkage between genes during evolutionary search allows the Linkage Tree Genetic Algorithm (LTGA) to maximize crossover effectiveness, greatly reducing both population size and total number of evaluations required to reach success on decomposable problems. This paper presents a comparative analysis of the most prominent LTGA variants and a newly introduced variant. While the deceptive trap problem (Trap-k) is one of the canonical benchmarks for testing LTGA, when LTGA is combined with applying steepest ascent hill climbing to the initial population, as is done in all significant LTGA variations, trap-k is trivially solved. This paper introduces the deceptive step trap problem (StepTrap-k,s), which shows the novel combination of smallest first subtree ordering with global mixing (LTS-GOMEA) is effective for black box optimization, while least linked first subtree ordering (LT-GOMEA) is effective on problems where partial reevaluation is possible. Finally, nearest neighbor NK landscapes show that global mixing is not effective on problems with complex overlapping linkage structure that cannot be modeled correctly by a linkage tree, emphasizing the need to extend how LTGA stores linkage to allow the power of global mixing to be applied to these types of problems.

Regression Testing for Model Transformations: A Multi-objective Approach

In current model-driven engineering practices, metamodels are modified followed by an update of transformation rules. Next, the updated transformation mechanism should be validated to ensure quality and robustness. Model transformation testing is a recently proposed effective technique used to validate transformation mechanisms. In this paper, a more efficient approach to model transformation testing is proposed by refactoring the existing test case models, employed to test previous metamodel and transformation mechanism versions, to cover new changes. To this end, a multi-objective optimization algorithm is employed to generate test case models that maximizes the coverage of the new metamodel while minimizing the number of test case model refactorings as well as test case model elements that have become invalid due to the new changes. Validation results on a widely used transformation mechanism confirm the effectiveness of our approach.

An exploration into dynamic population sizing

Traditional evolutionary algorithms are powerful problem solvers that have several fixed parameters which require prior specification. Determining good values for any of these parameters can be difficult, as these parameters are generally very sensitive, requiring expert knowledge to set optimally without extensive use of trial and error. Parameter control is a promising approach to achieving this automation and has the added potential of increasing EA performance based on both theoretical and empirical evidence that the optimal values of EA strategy parameters change during the course of executing an evolutionary run. While many methods of parameter control have been published that focus on removing the population size parameter, μ, all hampered by a variety of problems. This paper investigates the benefits of making μ a dynamic parameter and introduces two novel methods for population control. These methods are then compared to state-of-the-art population sizing EAs, exploring the strengths and weaknesses of each.