Algorithms for classification and partitioning in graphs / Algoritmos para problemas de classificação e particionamento em grafos
AUTOR(ES)
Luis Augusto Angelotti Meira
DATA DE PUBLICAÇÃO
2007
RESUMO
We present algorithms for combinatorial optimization NP-hard problems on classification and graph partitioning. The thesis concerns about theory and application and is guided by an approximation algorithms approach, complemented with heuristics and integer programming. We proposed good approximation factor algorithms as well as algorithms that find quality solutions in competitive time. We focus on three problems: the Metric Labeling Problem, the Sparsest Cut Problem and the Continuous Facility Location Problem. For the Metric Labeling Problem, we proposed an O(log n)-approximation algorithm. In the experimental analysis, this algorithm found high quality solutions in less time than other known algorithms. For the Sparsest Cut Problem we proposed heuristics and an exact algorithm. We built an SDP Solver to the relaxed formulation using a semi-infinity cut generation over linear programming. This approach considerably reduces the time used to solve the semi definite relaxation compared to an open source semi definite programming solver. Finally, for the Continuous Facility Location Problem we present approximation algorithms to the l2 and l2 2 distance function. These algorithms are used to obtain approximation algorithms to the k-Means Problem, which is a basic clustering problem. The presented algorithms are competitive since they obtain in many cases better solutions in equivalent time, compared to other known algorithms. The study of these problems results in three papers, which are detailed in chapters that make this thesis.
ASSUNTO(S)
combinatorial optimization algorithms integer programming algoritmos - programação otimização combinatoria programação inteira
