Tree ensembles are flexible predictive models that can capture relevant variables and to some extent their interactions in a compact and interpretable manner. Most algorithms for obtaining tree ensembles are based on versions of boosting or Random Forest. Previous work showed that boosting algorithms exhibit a cyclic behavior of selecting the same tree again and again due to the way the loss is...

The recent advances in genetic engineering, high powered computing and global optimization continue to stimulate interest in the area of molecular modeling and protein structure prediction. The goal of these eeorts is the ability to correctly predict native protein conformations and the binding interactions of macromolecules. These two problems currently dominate the eld of computational chemis...

The goal of this research is to provide practical solutions for covering problems. Covering problems arise in a variety of practical settings such as manufacturing, telecommunications, spatial query optimization, publish/subscribe middleware, graphics, molecular modeling, medical treatment and mobile military sensor coverage and targeting. For example, in the mobile sensor case a region is asso...

Motivated by an application in assortment planning under the nested logit choice model, we develop a polynomial-time approximation scheme for the sum-of-ratios optimization problem with a capacity constraint and a fixed number of product groups.

1 Copyright c © 2006 by ASME ABSTRACT We propose a novel approach to shape optimization that combines and retains the advantages of the earlier optimization techniques. The shapes in the design space are represented implicitly as level sets of a higher-dimensional function that is constructed using B-splines (to allow free-form deformations), and parameterized primitives combined with R-functio...

In this paper we consider a discrete choice model where heterogeneous agents are subject to mutual influences. We explore some consequences on the market’s behaviour, in the simplest case of a uniform willingness to pay distribution. We exhibit a first order phase transition in the profit optimisation by the monopolist: if the social influence is strong enough, there is a regime where, if the m...

The spreading of water across terrain is not a simple and isolated process. The spread of water is a part of the more general water cycle. Many commercial software exist for water modelling, but their correct use requires a considerable knowledge of water modelling, and about the study area. Using the relatively simple principle of cellular automata (CA) it is possible to obtain results which c...

Business analytics is becoming more and more important nowadays. Up to now predictive analytics appears to be much more applied in practice than prescriptive analytics. We argue that although optimization is used to obtain predictive models, and predictive tools are used to forecast parameters in optimization models, still the deep relation between the predictive and prescriptive analytics is n...

We describe a general framework for modelling probabilistic databases using factorization approaches. The framework includes tensor-based approaches which have been very successful in modelling triple-oriented databases and also includes recently developed neural network models. We consider the case that the target variable models the existence of a tuple, a continuous quantity associated with ...

The present paper emphasizes the potentialities of the industrial use of three-dimensional mathematical modelling of glass melting tanks for optimization of working conditions, design and control of indusaial furnaces. A short review of related recent relevant works is presented and industrial needs and requirements in modelling are discussed. A modelling procedure to solve the heat and mass tr...