Algorithm selection for sorting and probabilistic inference: a machine learning-based approach Export

@phdthesis{Guo2003PhD, abstract = {The algorithm selection problem aims at selecting the best algorithm for a given computational problem instance according to some characteristics of the instance. In this dissertation, we first introduce some results from theoretical investigation of the algorithm selection problem. We show, by Rice's theorem, the nonexistence of an automatic algorithm selection program based only on the description of the input instance and the competing hardness and algorithm performance based on Kolmogorov complexity to show that algorithm selection for search is also incomputable. Driven by the theoretical results, we propose a machine learning-based inductive approach using experimental algorithmic methods and machine learning techniques to solve the algorithm selection problem.}, address = {Manhattan, KS, USA}, author = {Guo, Haipeng}, citeulike-article-id = {5939615}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=979239}, citeulike-linkout-1 = {http://www.uic.edu.hk/~hpguo/thesis.pdf}, keywords = {algorithm-selection, algorithmic-complexity, bayes-networks, evolutionary-computation, no-free-lunch}, posted-at = {2009-10-14 16:03:11}, priority = {2}, publisher = {Kansas State University}, title = {Algorithm selection for sorting and probabilistic inference: a machine learning-based approach}, url = {http://portal.acm.org/citation.cfm?id=979239}, year = {2003} }

TY - THES ID - Guo2003PhD L3 - citeulike-article-id:5939615 N2 - The algorithm selection problem aims at selecting the best algorithm for a given computational problem instance according to some characteristics of the instance. In this dissertation, we first introduce some results from theoretical investigation of the algorithm selection problem. We show, by Rice's theorem, the nonexistence of an automatic algorithm selection program based only on the description of the input instance and the competing hardness and algorithm performance based on Kolmogorov complexity to show that algorithm selection for search is also incomputable. Driven by the theoretical results, we propose a machine learning-based inductive approach using experimental algorithmic methods and machine learning techniques to solve the algorithm selection problem. AD - Manhattan, KS, USA TI - Algorithm selection for sorting and probabilistic inference: a machine learning-based approach PB - Kansas State University KW - algorithm-selection KW - algorithmic-complexity KW - bayes-networks KW - evolutionary-computation KW - no-free-lunch AU - Guo, Haipeng PY - 2003/// UR - http://portal.acm.org/citation.cfm?id=979239 ER -