Welcome to STOPS project!

Methods that fit nonlinear distance transformations in multidimensional scaling and trade-off the fit with structure considerations to find optimal parameters.

This is the homepage of the Structure Optimized Proximity Scaling (STOPS) project that feature various extended and flexible Multidimensional Scaling approaches. On this page you can find links to related papers, talks, data and software.

Except noted otherwise, content on this homepage and this work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Papers:

Peer-reviewed Articles:

(all open access)

Rusch, T. (2025). Multidimensional Scaling With Heaviside Weighting: Extensions to Curvilinear Component Analysis and Curvilinear Distance AnalysisStat, 14:3,e70086.

Rusch, T., Mair, P., & Hornik, K. (2023). Structure-based Hyperparameter Selection with Bayesian optimization in Multidimensional Scaling, Statistics and Computing, 33:28.

Rusch, T., Mair, P., & Hornik, K. (2021) Cluster Optimized Proximity Scaling, Journal of Computational and Graphical Statistics, 30:4, 1156-1167.

Rusch, T., Hornik, K. & Mair, P. (2018) Assessing and Quantifying Clusteredness: The OPTICS Cordillera, Journal of Computational and Graphical Statistics, 27:1, 220-233.

Technical Reports:

Sparsified Multidimensional Scaling and Sparsified Multidimensional Distance Analysis
STOPS: Structure Optimized Proximity Scaling
COPS: Cluster Optimized Proximity Scaling
Assessing and Quantifying Clusteredness: The OPTICS Cordillera

Talks:

(title links lead to slides)

Title	Event	Date	Place
Manifold Learning with Extensions to CLCA and CLDA	Vienna Workshop of Model and Data Visualisation	01.07.2025	TU Vienna, Austria
Structure Optimized Proximity Scaling (STOPS): A Framework for Hyperparameter Selection in Multidimensional Scaling	Psychoco 2017	09.02.2017-10.02.2017	WU Vienna, Austria
COPS and STOPS: Cluster and/or Structure Optimized Proximity Scaling	Brown Bag Seminar, Institute for Statistics and Mathematics	07.12.2016	WU Vienna, Austria
The OPTICS Cordillera: Nonparametric Assessment of Clusteredness	Brown Bag Seminar, Institute for Statistics and Mathematics	23.10.2016	WU Vienna, Austria
COPS: Cluster Optimized Proximity Scaling	Psychoco 2015	12.02.2015-13.02.2015	Amsterdam, The Netherlands
Scaling for Clusters with COPS: Cluster Optimized Proximity Scaling	CFE-ERCIM 2014	06.12.2014-08.12.2014	Pisa, Italy

Software:

The project summary page you can find here.

The most recent builds of the software packages is available for Windows and Linux here: STOPS Package

People: