Another look at distance-weighted discrimination

Distance-weighted discrimination (DWD) is a modern margin-based classifier with an interesting geometric motivation. It was proposed as a competitor to the support vector machine (SVM). Despite many recent references on DWD, DWD is far less popular than the SVM, mainly because of computational and t...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of the Royal Statistical Society. Series B, Statistical methodology Ročník 80; číslo 1; s. 177 - 198
Hlavní autoři: Wang, Boxiang, Zou, Hui
Médium: Journal Article
Jazyk:angličtina
Vydáno: Oxford John Wiley & Sons Ltd 01.01.2018
Oxford University Press
Témata:
Algorithms
Bayes risk consistency
Bayesian analysis
Classification
Classifiers
Computation
data collection
Discrimination
Distance‐weighted discrimination
equations
Hilbert space
Kernel learning
Learning
Learning theories
Learning theory
Machine learning
Majorization–minimization principle
Motivation
Novels
Regression analysis
risk
Second‐order cone programming
Statistical methods
Statistics
Support vector machines
ISSN:1369-7412, 1467-9868
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Distance-weighted discrimination (DWD) is a modern margin-based classifier with an interesting geometric motivation. It was proposed as a competitor to the support vector machine (SVM). Despite many recent references on DWD, DWD is far less popular than the SVM, mainly because of computational and theoretical reasons. We greatly advance the current DWD methodology and its learning theory. We propose a novel thrifty algorithm for solving standard DWD and generalized DWD, and our algorithm can be several hundred times faster than the existing state of the art algorithm based on second-order cone programming. In addition, we exploit the new algorithm to design an efficient scheme to tune generalized DWD. Furthermore, we formulate a natural kernel DWD approach in a reproducing kernel Hubert space and then establish the Bayes risk consistency of the kernel DWD by using a universal kernel such as the Gaussian kernel. This result solves an open theoretical problem in the DWD literature. A comparison study on 16 benchmark data sets shows that data-driven generalized DWD consistently delivers higher classification accuracy with less computation time than the SVM.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1369-7412
1467-9868
DOI:10.1111/rssb.12244