Abstract | ||
---|---|---|
Akaike's information criterion (AIC) is a measure of the quality of a statistical model for a given set of data. We can determine the best statistical model for a particular data set by the minimization based on the AIC. Since it is difficult to find the best statistical model from a set of candidates by this minimization in practice, stepwise methods, which are local search algorithms, are commonly used to find a better statistical model though it may not be the best. We formulate this AIC minimization as a mixed integer nonlinear programming problem and propose a method to find the best statistical model. In particular, we propose ways to find lower and upper bounds and a branching rule for this minimization. We then combine them with SCIP, which is a mathematical optimization software and a branch-and-bound framework. We show that the proposed method can provide the best statistical model based on AIC for small-sized or medium-sized benchmark data sets in UCI Machine Learning Repository. Furthermore, we show that this method can find good quality solutions for large-sized benchmark data sets. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-42432-3_36 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
Mixed integer nonlinear program,SCIP,Akaike's information criterion | Integer,Discrete mathematics,Mathematical optimization,Bayesian information criterion,Akaike information criterion,Nonlinear system,Computer science,Minification,Statistical model,Local search (optimization) | Conference |
Volume | ISSN | Citations |
9725 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 5 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Keiji Kimura | 1 | 0 | 0.34 |
Hayato Waki | 2 | 376 | 28.82 |