Frédéric Saubion

Autonomous operator management for evolutionary algorithms

The performance of an evolutionary algorithm strongly depends on the design of its operators and on the management of these operators along the search; that is, on the ability of the algorithm to balance exploration and exploitation of the search space. Recent approaches automate the tuning and control of the parameters that govern this balance. We propose a new technique to dynamically control the behavior of operators in an EA and to manage a large set of potential operators. The best operators are rewarded by applying them more often. Tests of this technique on instances of 3-SAT return results that are competitive with an algorithm tailored to the problem.

GASAT: a genetic local search algorithm for the satisfiability problem

This paper presents GASAT, a hybrid algorithm for the satisfiability problem (SAT). The main feature of GASAT is that it includes a recombination stage based on a specific crossover and a tabu search stage. We have conducted experiments to evaluate the different components of GASAT and to compare its overall performance with state-of-the-art SAT algorithms. These experiments show that GASAT provides very competitive results.

Extreme compass and Dynamic Multi-Armed Bandits for Adaptive Operator Selection

The goal of Adaptive Operator Selection is the on-line control of the choice of variation operators within Evolutionary Algorithms. The control process is based on two main components, the credit assignment, that defines the reward that will be used to evaluate the quality of an operator after it has been applied, and the operator selection mechanism, that selects one operator based on some operators qualities. Two previously developed Adaptive Operator Selection methods are combined here: Compass evaluates the performance of operators by considering not only the fitness improvements from parent to offspring, but also the way they modify the diversity of the population, and their execution time; Dynamic Multi-Armed Bandit proposes a selection strategy based on the well-known UCB algorithm, achieving a compromise between exploitation and exploration, while nevertheless quickly adapting to changes. Tests with the proposed method, called ExCoDyMAB, are carried out using several hard instances of the Satisfiability problem (SAT). Results show the good synergetic effect of combining both approaches.

On Evaluation Methodologies for Text Segmentation Algorithms

In this work an image retrieval system adaptable to users interests by the use of relevance feedback via genetic algorithm is presented. The retrieval process is based on local similarity patterns. The goal of the genetic algorithm is to infer weights for regions and features that better translate the users requirements producing better quality rankings. The genetic algorithm used has as its main innovation an order-based fitness function, which is appropriate to the ranking requirements of a majority of the users. This fitness function will quickly drive the genetic algorithm in the process of searching for an optimal solution. Evaluations in several databases have shown the robustness and efficiency of the proposed retrieval method even when the query is a sketch or damaged image.The WindowDiff evaluation measure (Pevzner and Hearst, 2002) is becoming the standard criterion for evaluating text segmentation methods. Nevertheless, this metric is really not fair with regard to the characteristics of the methods and the results that it provides on different kinds of corpus are difficult to compare. Therefore, we first attempt to improve this measure according to the risks taken by each method on different kinds of text. On the other hand, the production of a segmentation of reference being a rather difficult task, this paper describes a new evaluation metric that relies on the stability of the segmentations face to text transformations. Our experimental results appear to indicate that both proposed metrics provide really better indicators of the text segmentation accuracy than existing measures.

Evolutionary computing for the satisfiability problem

This paper presents GASAT, a hybrid evolutionary algorithm for the satisfiability problem (SAT). A specific crossover operator generates new solutions, that are improved by a tabu search procedure. The performance of GASAT is assessed using a set of well-known benchmarks. Comparisons with state-of-the-art SAT algorithms show that GASAT gives very competitive results. These experiments also allow us to introduce a new SAT benchmark from a coloring problem.

A dynamic island model for adaptive operator selection

In this paper we propose a generic framework for Dynamic Island Models, which can be used as an original approach for the adaptive selection of operators in evolutionary algorithms. Assigning a variation operator to each island, we show that the dynamic regulation of migrations, which takes into account the pertinence of recent migrations, distributes the individuals on the most promising islands, i.e., the most efficient operators, at each stage of the search. The efficiency of this approach is assessed on the One-Max problem by comparing theoretical expected results to those obtained by our dynamic island model. Experiments show that the model provides the expected behavior.

On Hybridization of Local Search and Constraint Propagation

Hybridization of local search and constraint programming techniques for solving Constraint Satisfaction Problems is generally restricted to some kind of master-slave combinations for specific classes of problems. In this paper we propose a theoretical model based on K.R. Apt’s chaotic iterations for hybridization of local search and constraint propagation. Hybrid resolution can be achieved as the computation of a fixpoint of some specific reduction functions. Our framework opens up new and finer possibilities for hybridization/combination strategies. We also present some combinations of techniques such as tabu search, node and bound consistencies. Some experimental results show the interest of our model to design such hybridization.

On the design of adaptive control strategies for evolutionary algorithms

This paper focuses on the design of control strategies forEvolutionary Algorithms. We propose a method to encapsulate multipleparameters, reducing control to only one criterion. This method allowsto define generic control strategies independently from both the algorithmsoperators and the problem to be solved. Three strategies areproposed and compared on a classical optimization problem, consideringtheir generality and performance.

A multiplex-PCR assay for identification of the quarantine plant pathogen Xanthomonas axonopodis pv. phaseoli.

In this study we developed an algorithm to screen for all exact molecular signatures of the quarantine pathogen Xanthomonas axonopodis pv. phaseoli (Xap), based on available data of the presence or absence of virulence-associated genes. The simultaneous presence of genes avrBsT and xopL is specific to Xap. Therefore we developed a multiplex PCR assay targeting avrBsT and xopL for the molecular identification of Xap. The specificity of this multiplex was validated by comparison to that of other molecular identification assays aimed at Xap, on a wide collection of reference strains. This multiplex was further validated on a blind collection of Xanthomonas isolates for which pathogenicity was assayed by stem wounding and by dipping leaves into calibrated inocula. This multiplex was combined to the previously described X4c/X4e molecular identification assay for Xap. Such a combination enables the molecular identification of all strains of Xanthomonas pathogenic on bean. Results also show that assay by stem wounding does not give reliable results in the case of Xap, and that pathogenicity assays by dipping should be preferred.

An exploration-exploitation compromise-based adaptive operator selection for local search

This paper deals with the adaptive selection of operators in the context of local search (LS). In evolutionary algorithms, diversity is a key concept. We consider a related idea: the similarity between the candidate solution and the solutions in the search trajectory. This notion, together with the solution quality, is used to evaluate the performance of each operator. A new utility measure for LS operators, evaluating relative distances between the operators, is introduced. It is compared with an existing measure based on the Pareto dominance relationship using some basic selection schemes. An adaptive version of the algorithm is also examined. The proposed methods are tested on the Quadratic Assignment Problem and Asymmetric Traveling Salesman Problem.