English

Global Minima by Penalized Full-dimensional Scaling

Computation 2024-07-24 v1 Machine Learning

Abstract

The full-dimensional (metric, Euclidean, least squares) multidimensional scaling stress loss function is combined with a quadratic external penalty function term. The trajectory of minimizers of stress for increasing values of the penalty parameter is then used to find (tentative) global minima for low-dimensional multidimensional scaling. This is illustrated with several one-dimensional and two-dimensional examples.

Keywords

Cite

@article{arxiv.2407.16645,
  title  = {Global Minima by Penalized Full-dimensional Scaling},
  author = {Jan de Leeuw},
  journal= {arXiv preprint arXiv:2407.16645},
  year   = {2024}
}

Comments

39 pages

R2 v1 2026-06-28T17:51:08.870Z