Survey of mathematical programming models and experimental results for linear discriminant analysis

By S. Erenguc, Gary J. Koehler. 1990

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Supersparse linear integer models for optimized medical scoring systems (2015, background): “(Mangasarian, 1994, Asparoukhov and Stam, 1997, Rubin, 2009). Early attempts at this problem were only feasible for tiny datasets with at most N= 200 examples (see e.g. Joachimsthaler and Stam, 1990, Erenguc and Koehler, 1990). Since then, a large body of work has aimed to improve scalability by mod”
Methods and Models for Interpretable Linear Classification (2014, background): “Early attempts at misclassification minimization were only feasible for tiny datasets with at most N = 200 examples [54, 31].”
A Mixed-Integer Programming Approach to Multi-Class Data Classification Problem by (2005, background): “An extension and a complement to this, Erenguc and Koehler made a comprehensive review [32].”
Solving mixed integer classification problems by decomposition (1997, background): “Subsequently, a number of authors experimented with linear [ 5 , 9, 10, 13, 14, 16, 18, 21, 26] and integer [1, 11, 12, 20, 32, 34] programming models for selecting discriminant functions; since then, more esoteric approaches, including nonlinear programming [3, 33] and neural networks [4, 25, 35, 3”