Distance-Weighted Discrimination
- 1 December 2007
- journal article
- Published by Informa UK Limited in Journal of the American Statistical Association
- Vol. 102 (480), 1267-1271
- https://doi.org/10.1198/016214507000001120
Abstract
High-dimension low–sample size statistical analysis is becoming increasingly important in a wide range of applied contexts. In such situations, the popular support vector machine suffers from "data piling" at the margin, which can diminish generalizability. This leads naturally to the development of distance-weighted discrimination, which is based on second-order cone programming, a modern computationally intensive optimization method.Keywords
This publication has 8 references indexed in Scilit:
- The high-dimension, low-sample-size geometric representation holds under mild conditionsBiometrika, 2007
- Geometric Representation of High Dimension, Low Sample Size DataJournal of the Royal Statistical Society Series B: Statistical Methodology, 2005
- Adjustment of systematic microarray data biasesBioinformatics, 2004
- Solving semidefinite-quadratic-linear programs using SDPT3Mathematical Programming, 2003
- Second-order cone programmingMathematical Programming, 2003
- Robust set separation via exponentialsNonlinear Analysis, 2001
- Distinctive gene expression patterns in human mammary epithelial cells and breast cancersProceedings of the National Academy of Sciences, 1999
- Ridge Estimators in Logistic RegressionJournal of the Royal Statistical Society Series C: Applied Statistics, 1992