Marta Soto

• Ph.D.
• Instituto de Cibernética Matemática y Física

The aim of this work is studying the use of copulas and vines in numerical optimization with Estimation of Distribution Algorithms (EDAs). Two EDAs built around the multivariate product and normal copulas, and other two based on pair-copula decomposition of vine models are studied. We analyze empirically the effect of both marginal distributions an...

Computer modeling of protein-ligand interactions is one of the most important phases in a drug design process. Part of the process involves the optimization of highly multi-modal objective (scoring) functions. This research presents the Minimum Population Search heuristic as an alternative for solving these global unconstrained optimization problem...

The use of copula-based models in EDAs (estimation of distribution algorithms) is currently an active area of research. In this context, the copulaedas package for R provides a platform where EDAs based on copulas can be implemented and studied. The package offers complete implementations of various EDAs based on copulas and vines, a group of well-...

The use of probabilistic models based on copulas in Estimation of Distribution Algorithms (EDAs) has been identified as an emerging research trend on these algorithms for continuous domains. By using copulas, the effect of the dependence structure and the margins in a joint distribution can be represented separately. Consequently, EDAs based on cop...

The use of copula-based models in EDAs (estimation of distribution algorithms) is currently an active area of research. In this context, the copulaedas package for R provides a platform where EDAs based on copulas can be implemented and studied. The package offers complete implementations of various EDAs based on copulas and vines, a group of well-...

A Vine Estimation of Distribution Algorithm (VEDA) is a recently proposed optimization procedure built on top of a probabilistic graphical model called vine. The first target of vines was uncertainty analysis with high dimensional dependence modeling. The aim of this communication is to draw a path through a simple set of experiments, from the Univ...

Four undirected graphical models based on copula theory are investigated in relation to their use within an estimation of distribution algorithm (EDA) to address the molecular docking problem. The simplest algorithms considered are built on top of the product and normal copulas. The other two construct high-dimensional dependence models using the p...

This paper introduces a novel method for ellipse detection that is based on Estimation of Distribution Algorithms. The main contribution is the construction of a new fitness function model that in contrast to existing methods can assign positive evaluations to ellipses that do not exist in the image. This approach produces much smoother fitness lan...

Los algoritmos evolutivos con estimación de distribuciones son una herramienta relativamente nueva de la computación evolutiva donde los operadores de recombinación y mutación son reemplazados por un operador que estima la distribución de probabilidad del conjunto de puntos seleccionados. Estimar la distribución de probabilidad es el paso más impor...

A new class of estimation of distribution algorithms (EDAs), known as cellular EDAs (cEDAs), has recently emerged. In these algo- rithms, the population is decentralized by partitioning it into many small collaborating subpopulations, arranged in a toroidal grid, and interacting only with its neighboring subpopulations. In this work, we study the s...

The success of evolutionary algorithms, in particular Factorized Distribution Algorithms (FDA), for many pattern recognition tasks heavily depends on our ability to reduce the number of function evaluations. This paper introduces a method to reduce the population size overhead. We use low order marginals during the learning step and then compute th...

In this paper a tree based Factorized Distribution Algorithm for the solution of integer problems is introduced. Our proposal combines classical methods for structural learning of dependencies with a a procedures that approximates the bivariate marginals by sampling the data using auxiliary tables. Experiments done for a number of problems with an...

This short paper surveys current work on the use of Factorized Distribution Algorithms for the solution of combinatorial optimization problems denned on graphs. We also advance a number of approaches for future work along this line

A Factorized Distribution algorithm that use up to pairwise dependencies for the optimization of integer problems is introduced. Our proposal combines classical methods for structural learning of dependencies with a procedure that approximates the bivariate marginals by sampling the data using auxiliary tables. The algorithm overperforms the Univar...

Single connected Factorized Distribution Algorithms (FDA-SC) use factorizations of the joint distribution, which are trees, forests or polytrees. At each stage of the evolution they build a polytree from which new points are sampled. We study empirically the relation between the accuracy of the learned model and the quality of the new search points...

The goal of this research is to analyze how individual learning interacts with an evolutionary algorithm in its search for best candidates for the Busy Beaver problem. To study this interaction two learning models, implemented as local search procedures, are proposed. Experimental results show that, in highly irregular and prone to premature conver...

The class of factorized distribution algorithms (FDA) uses factorizations of the joint distribution of the best points. At each stage of the evolution, PDA algorithms build a model from which new points are efficiently sampled. This paper explores the class of single connected factorizations: polytrees. Using this class, we gain in efficiency and s...

The goal of this research is to analyze how individual learning interacts with an evolutionary algorithm in its search for best candidates for the Busy Beaver problem. To study this interaction, two learning models, implemented as local search procedures, are proposed. Experimental results show that, in highly irregular search spaces that are prone...

This paper extends the FDA - the Factorized Distribution Algorithm - with a structural learning component. The FDA has been extensively investigated for the optimization of additively decomposed discrete functions (ADFs). Now, we are able to deal with more general problems, which are solved by FDA in a blackbox optimization scenario. The key point...

This chapter presents results on the application of the concept of entropy to estimation of distribution algorithms (EDAs). Firstly, the Boltzmann mutual information curves are introduced. They are shown to contain a lot of information about the difficulty of the functions. Next, a design method of discrete benchmark functions is presented. The new...

The method of partial evaluation of genetic algorithms is aimed to deal with costly fitness functions. In many cases, it consists in constructing a mode of the relation between the fitness of an offspring and the information associated to the evolution process that led to its creation. This paper approaches issues related to the construction of PE-...

We present a Factorized Distribution Algorithm (FDA) for the optimization of constrained problems where the constraints are expressed in terms of the unitation values of the function. The algorithm uses information about the structure of the problem to conduct the search in the space of feasible solutions. Thus, we present a number of ways FDAs can...

We have already introduced the concept of Partial Evaluation (PE) in Genetic Algorithms (GAs) in order to deal with costly fitness functions. A GAs can be costly for many reasons and the problems are highlighted when a user tries to evaluate the solutions presented by the GAs, or when too much time or resources are required to evaluate the objectiv...