Combinatorial individual differences scaling within the city-block metric

Research output: Contribution to journalArticle

Abstract

A new method is proposed for conducting individual differences scaling within the city-block metric that does not rely on gradient- or subgradient-based optimization. Instead, a combinatorial optimization scheme is utilized for identifying object coordinates minimizing the least-squares loss function. The illustrative application of combinatorial individual differences scaling within the city-block metric to schematic face stimuli suggests that the new method offers a promising alternative to gradient-based attempts for fitting city-block scaling models, which suffer from the well-documented difficulty of local minima.

Original languageEnglish (US)
Pages (from-to)931-946
Number of pages16
JournalComputational Statistics and Data Analysis
Volume51
Issue number2
DOIs
StatePublished - Nov 15 2006

Fingerprint

Individual Differences
Combinatorial optimization
Schematic diagrams
Scaling
Metric
Gradient
Square Functions
Subgradient
Combinatorial Optimization
Loss Function
Local Minima
Least Squares
Face
Optimization
Alternatives
Individual differences
Model

Keywords

  • City-block metric
  • Combinatorial data analysis
  • Combinatorial optimization
  • INDSCAL model
  • Individual differences scaling
  • Iterative projection
  • Quadratic assignment
  • Uni-/multidimensional scaling

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Statistics, Probability and Uncertainty
  • Electrical and Electronic Engineering
  • Computational Mathematics
  • Numerical Analysis
  • Statistics and Probability

Cite this

Combinatorial individual differences scaling within the city-block metric. / Koehn, Hans Friedrich.

In: Computational Statistics and Data Analysis, Vol. 51, No. 2, 15.11.2006, p. 931-946.

Research output: Contribution to journalArticle

@article{904fd38093584059848d3a10f6c91a66,
title = "Combinatorial individual differences scaling within the city-block metric",
abstract = "A new method is proposed for conducting individual differences scaling within the city-block metric that does not rely on gradient- or subgradient-based optimization. Instead, a combinatorial optimization scheme is utilized for identifying object coordinates minimizing the least-squares loss function. The illustrative application of combinatorial individual differences scaling within the city-block metric to schematic face stimuli suggests that the new method offers a promising alternative to gradient-based attempts for fitting city-block scaling models, which suffer from the well-documented difficulty of local minima.",
keywords = "City-block metric, Combinatorial data analysis, Combinatorial optimization, INDSCAL model, Individual differences scaling, Iterative projection, Quadratic assignment, Uni-/multidimensional scaling",
author = "Koehn, {Hans Friedrich}",
year = "2006",
month = "11",
day = "15",
doi = "10.1016/j.csda.2005.09.013",
language = "English (US)",
volume = "51",
pages = "931--946",
journal = "Computational Statistics and Data Analysis",
issn = "0167-9473",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Combinatorial individual differences scaling within the city-block metric

AU - Koehn, Hans Friedrich

PY - 2006/11/15

Y1 - 2006/11/15

N2 - A new method is proposed for conducting individual differences scaling within the city-block metric that does not rely on gradient- or subgradient-based optimization. Instead, a combinatorial optimization scheme is utilized for identifying object coordinates minimizing the least-squares loss function. The illustrative application of combinatorial individual differences scaling within the city-block metric to schematic face stimuli suggests that the new method offers a promising alternative to gradient-based attempts for fitting city-block scaling models, which suffer from the well-documented difficulty of local minima.

AB - A new method is proposed for conducting individual differences scaling within the city-block metric that does not rely on gradient- or subgradient-based optimization. Instead, a combinatorial optimization scheme is utilized for identifying object coordinates minimizing the least-squares loss function. The illustrative application of combinatorial individual differences scaling within the city-block metric to schematic face stimuli suggests that the new method offers a promising alternative to gradient-based attempts for fitting city-block scaling models, which suffer from the well-documented difficulty of local minima.

KW - City-block metric

KW - Combinatorial data analysis

KW - Combinatorial optimization

KW - INDSCAL model

KW - Individual differences scaling

KW - Iterative projection

KW - Quadratic assignment

KW - Uni-/multidimensional scaling

UR - http://www.scopus.com/inward/record.url?scp=33750359842&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750359842&partnerID=8YFLogxK

U2 - 10.1016/j.csda.2005.09.013

DO - 10.1016/j.csda.2005.09.013

M3 - Article

AN - SCOPUS:33750359842

VL - 51

SP - 931

EP - 946

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

SN - 0167-9473

IS - 2

ER -