Multidimensional Scaling and Genetic Algorithms : A Solution Approach to Avoid Local Minima

Arbeitspapier

Multidimensional scaling is very common in exploratory data analysis. It is mainly used to represent sets of objects with respect to their proximities in a low dimensional Euclidean space. Widely used optimization algorithms try to improve the representation via shifting its coordinates in direction of the negative gradient of a corresponding fit function. Depending on the initial configuration, the chosen algorithm and its parameter settings there is a possibility for the algorithm to terminate in a local minimum. This article describes the combination of an evolutionary model with a non-metric gradient solution method to avoid this problem. Furthermore a simulation study compares the results of the evolutionary approach with one classic solution method.

Object Details

• Language: Englisch

References and Relationships

• Bibliographic citation: Series: Arbeitspapiere zur mathematischen Wirtschaftsforschung ; No. 181

Classification and Topics

• Classification: Wirtschaft
• Subject: Heuristisches Verfahren ; Mathematische Optimierung ; Theorie

Contributors, Places and Time

• Event: Geistige Schöpfung
• (who): Etschberger, Stefan ; Hilbert, Andreas
• Event: Veröffentlichung
• (who): Universität Augsburg, Institut für Statistik und Mathematische Wirtschaftstheorie
• (where): Augsburg
• (when): 2002

Further information

• Handle: http://hdl.handle.net/10419/22817
• Last update: 10.03.2025, 11:43 AM CET