Constructing boosting algorithms from SVMs: An application to one-class classification

Gunnar Rätsch, Sebastian Mika, Bernhard Schölkopf, Klaus Muller

Research output: Contribution to journalArticle

160 Citations (Scopus)

Abstract

We show via an equivalence of mathematical programs that a support vector (SV) algorithm can be translated into an equivalent boosting-like algorithm and vice versa. We exemplify this translation procedure for a new algorithm-one-class leveraging-starting from the one-class support vector machine (1-SVM). This is a first step toward unsupervised learning in a boosting framework. Building on so-called barrier methods known from the theory of constrained optimization, it returns a function, written as a convex combination of base hypotheses, that characterizes whether a given test point is likely to have been generated from the distribution underlying the training data. Simulations on one-class classification problems demonstrate the usefulness of our approach.

Original languageEnglish
Pages (from-to)1184-1199
Number of pages16
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume24
Issue number9
DOIs
Publication statusPublished - 2002 Sep 1
Externally publishedYes

Fingerprint

One-class Classification
Boosting
Barrier Methods
Unsupervised learning
Support Vector
Unsupervised Learning
Convex Combination
Constrained optimization
Constrained Optimization
Classification Problems
Support vector machines
Support Vector Machine
Likely
Equivalence
Learning
Demonstrate
Simulation
Class

Keywords

  • Boosting
  • Novelty detection
  • One-class classification
  • SVMs
  • Unsupervised learning

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition

Cite this

Constructing boosting algorithms from SVMs : An application to one-class classification. / Rätsch, Gunnar; Mika, Sebastian; Schölkopf, Bernhard; Muller, Klaus.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 9, 01.09.2002, p. 1184-1199.

Research output: Contribution to journalArticle

Rätsch, Gunnar ; Mika, Sebastian ; Schölkopf, Bernhard ; Muller, Klaus. / Constructing boosting algorithms from SVMs : An application to one-class classification. In: IEEE Transactions on Pattern Analysis and Machine Intelligence. 2002 ; Vol. 24, No. 9. pp. 1184-1199.
@article{aa66222681a14bc4b56abe1705d32a6d,
title = "Constructing boosting algorithms from SVMs: An application to one-class classification",
abstract = "We show via an equivalence of mathematical programs that a support vector (SV) algorithm can be translated into an equivalent boosting-like algorithm and vice versa. We exemplify this translation procedure for a new algorithm-one-class leveraging-starting from the one-class support vector machine (1-SVM). This is a first step toward unsupervised learning in a boosting framework. Building on so-called barrier methods known from the theory of constrained optimization, it returns a function, written as a convex combination of base hypotheses, that characterizes whether a given test point is likely to have been generated from the distribution underlying the training data. Simulations on one-class classification problems demonstrate the usefulness of our approach.",
keywords = "Boosting, Novelty detection, One-class classification, SVMs, Unsupervised learning",
author = "Gunnar R{\"a}tsch and Sebastian Mika and Bernhard Sch{\"o}lkopf and Klaus Muller",
year = "2002",
month = "9",
day = "1",
doi = "10.1109/TPAMI.2002.1033211",
language = "English",
volume = "24",
pages = "1184--1199",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "9",

}

TY - JOUR

T1 - Constructing boosting algorithms from SVMs

T2 - An application to one-class classification

AU - Rätsch, Gunnar

AU - Mika, Sebastian

AU - Schölkopf, Bernhard

AU - Muller, Klaus

PY - 2002/9/1

Y1 - 2002/9/1

N2 - We show via an equivalence of mathematical programs that a support vector (SV) algorithm can be translated into an equivalent boosting-like algorithm and vice versa. We exemplify this translation procedure for a new algorithm-one-class leveraging-starting from the one-class support vector machine (1-SVM). This is a first step toward unsupervised learning in a boosting framework. Building on so-called barrier methods known from the theory of constrained optimization, it returns a function, written as a convex combination of base hypotheses, that characterizes whether a given test point is likely to have been generated from the distribution underlying the training data. Simulations on one-class classification problems demonstrate the usefulness of our approach.

AB - We show via an equivalence of mathematical programs that a support vector (SV) algorithm can be translated into an equivalent boosting-like algorithm and vice versa. We exemplify this translation procedure for a new algorithm-one-class leveraging-starting from the one-class support vector machine (1-SVM). This is a first step toward unsupervised learning in a boosting framework. Building on so-called barrier methods known from the theory of constrained optimization, it returns a function, written as a convex combination of base hypotheses, that characterizes whether a given test point is likely to have been generated from the distribution underlying the training data. Simulations on one-class classification problems demonstrate the usefulness of our approach.

KW - Boosting

KW - Novelty detection

KW - One-class classification

KW - SVMs

KW - Unsupervised learning

UR - http://www.scopus.com/inward/record.url?scp=0036709275&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036709275&partnerID=8YFLogxK

U2 - 10.1109/TPAMI.2002.1033211

DO - 10.1109/TPAMI.2002.1033211

M3 - Article

AN - SCOPUS:0036709275

VL - 24

SP - 1184

EP - 1199

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 9

ER -