Compact MILP models for optimal and Pareto-optimal LAD patterns

Authors:
Cui Guo;Hong Seo Ryoo
Affiliations:
Graduate School of Information Management & Security, Korea University, 1, 5-Ga, Anam-Dong, Seongbuk-Gu, Seoul, 136-713, Republic of Korea;School of Industrial Management Engineering, Korea University, 1, 5-Ga, Anam-Dong, Seongbuk-Gu, Seoul, 136-713, Republic of Korea
Venue:
Discrete Applied Mathematics
Year:
2012

Citing 10
Cited 0

Occam's razor

Information Processing Letters
Very Simple Classification Rules Perform Well on Most Commonly Used Datasets

Machine Learning
Logical analysis of numerical data

Mathematical Programming: Series A and B - Special issue: papers from ismp97, the 16th international symposium on mathematical programming, Lausanne EPFL
An Implementation of Logical Analysis of Data

IEEE Transactions on Knowledge and Data Engineering
Pareto-optimal patterns in logical analysis of data

Discrete Applied Mathematics - Discrete mathematics & data mining (DM & DM)
Logical analysis of data --- the vision of Peter L. Hammer

Annals of Mathematics and Artificial Intelligence
Maximum patterns in datasets

Discrete Applied Mathematics
Comprehensive vs. comprehensible classifiers in logical analysis of data

Discrete Applied Mathematics
MILP approach to pattern generation in logical analysis of data

Discrete Applied Mathematics
Spanned patterns for the logical analysis of data

Discrete Applied Mathematics - Special issue: Discrete mathematics & data mining II (DM & DM II)

Quantified Score

Hi-index	0.04

Visualization

Abstract

This paper develops MILP models for various optimal and Pareto-optimal LAD patterns that involve at most 2n 0-1 decision variables, where n is the number of support features for the data under analysis, which usually is small. Noting that the previous MILP pattern generation models are defined in 2n+m 0-1 variables, where m is the number of observations in the dataset with m@?n in general, the new models are expected to generate useful LAD patterns more efficiently. With experiments on six well-studied machine learning datasets, we first demonstrate the efficiency of the new MILP models and next use them to show different utilities of strong prime patterns and strong spanned patterns in enhancing the overall classification accuracy of a LAD decision theory.