Search

Recent years have witnessed a growing interest in automatic learning mechanisms and applications. The concept of hyper-heuristics, algorithms that either select among existing algorithms or generate new ones, holds high relevance in this matter. Current research suggests that, under certain circumstances, hyper-heuristics outperform single heuristics when evaluated in isolation. When hyper-heuristics are selected among existing algorithms, they map problem states into suitable solvers. Unfortunately, identifying the features that accurately describe the problem state—and thus allow for a proper mapping—requires plenty of domain-specific knowledge, which is not always available. This work proposes a simple yet effective hyper-heuristic model that does not rely on problem features to produce such a mapping. The model defines a fixed sequence of heuristics that improves the solving process of knapsack problems. This research comprises an analysis of feature-independent hyper-heuristic performance under different learning conditions and different problem sets. [ABSTRACT FROM AUTHOR]

Many of the works conducted on algorithm selection strategies—methods that choose a suitable solving method for a particular problem—start from scratch since only a few investigations on reusable components of such methods are found in the literature. Additionally, researchers might unintentionally omit some implementation details when documenting the algorithm selection strategy. This makes it difficult for others to reproduce the behavior obtained by such an approach. To address these problems, we propose to rely on existing techniques from the Machine Learning realm to speed-up the generation of algorithm selection strategies while improving the modularity and reproducibility of the research. The proposed solution model is implemented on a domain-independent Machine Learning module that executes the core mechanism of the algorithm selection task. The algorithm selection strategies produced in this work are implemented and tested rapidly compared against the time it would take to build a similar approach from scratch. We produce four novel algorithm selectors based on Machine Learning for constraint satisfaction problems to verify our approach. Our data suggest that these algorithms outperform the best performing algorithm on a set of test instances. For example, the algorithm selectors Multiclass Neural Network (MNN) and Multiclass Logistic Regression (MLR), powered by a neural network and linear regression, respectively, reduced the search cost (in terms of consistency checks) of the best performing heuristic (KAPPA), on average, by 49% for the instances considered for this work. [ABSTRACT FROM AUTHOR]

Constraint satisfaction problems are of special interest for the artificial intelligence and operations research community due to their many applications. Although heuristics involved in solving these problems have largely been studied in the past, little is known about the relation between instances and the respective performance of the heuristics used to solve them. This paper focuses on both the exploration of the instance space to identify relations between instances and good performing heuristics and how to use such relations to improve the search. Firstly, the document describes a methodology to explore the instance space of constraint satisfaction problems and evaluate the corresponding performance of six variable ordering heuristics for such instances in order to find regions on the instance space where some heuristics outperform the others. Analyzing such regions favors the understanding of how these heuristics work and contribute to their improvement. Secondly, we use the information gathered from the first stage to predict the most suitable heuristic to use according to the features of the instance currently being solved. This approach proved to be competitive when compared against the heuristics applied in isolation on both randomly generated and structured instances of constraint satisfaction problems. [ABSTRACT FROM AUTHOR]

Metaheuristics have become a widely used approach for solving a variety of practical problems. The literature is full of diverse metaheuristics based on outstanding ideas and with proven excellent capabilities. Nonetheless, oftentimes metaheuristics claim novelty when they are just recombining elements from other methods. Hence, the need for a standard metaheuristic model is vital to stop the current frenetic tendency of proposing methods chiefly based on their inspirational source. This work introduces a first step to a generalised and mathematically formal metaheuristic model, which can be used for studying and improving them. This model is based on a scheme of simple heuristics, which perform as building blocks that can be modified depending on the application. For this purpose, we define and detail all components and concepts of a metaheuristic (i.e., its search operators), such as heuristics. Furthermore, we also provide some ideas to take into account for exploring other search operator configurations in the future. To illustrate the proposed model, we analyse search operators from four well-known metaheuristics employed in continuous optimisation problems as a proof-of-concept. From them, we derive 20 different approaches and use them for solving some benchmark functions with different landscapes. Data show the remarkable capability of our methodology for building metaheuristics and detecting which operator to choose depending on the problem to solve. Moreover, we outline and discuss several future extensions of this model to various problem and solver domains. [ABSTRACT FROM AUTHOR]