Multidimensional Scaling, Sammon Mapping, and Isomap: Tutorial and Survey

Abstract

Multidimensional Scaling (MDS) is one of the first fundamental manifold learning methods. It can be categorized into several methods, i.e., classical MDS, kernel classical MDS, metric MDS, and non-metric MDS. Sammon mapping and Isomap can be considered as special cases of metric MDS and kernel classical MDS, respectively. In this tutorial and survey paper, we review the theory of MDS, Sammon mapping, and Isomap in detail. We explain all the mentioned categories of MDS. Then, Sammon mapping, Isomap, and kernel Isomap are explained. Out-of-sample embedding for MDS and Isomap using eigenfunctions and kernel mapping are introduced. Then, Nystrom approximation and its use in landmark MDS and landmark Isomap are introduced for big data embedding. We also provide some simulations for illustrating the embedding by these methods.

To appear as a part of an upcoming academic book on dimensionality reduction and manifold learning

References in corpus (3)

• Eigenvalue and Generalized Eigenvalue Problems: Tutorial
• Feature Selection and Feature Extraction in Pattern Analysis: A Literature Review
• Unsupervised and Supervised Principal Component Analysis: Tutorial

Cited by in corpus (7)

• Linear and Nonlinear Dimensionality Reduction from Fluid Mechanics to Machine Learning
• Locally Linear Embedding and its Variants: Tutorial and Survey
• Reproducing Kernel Hilbert Space, Mercer's Theorem, Eigenfunctions, Nyström Method, and Use of Kernels in Machine Learning: Tutorial and Survey
• Laplacian-Based Dimensionality Reduction Including Spectral Clustering, Laplacian Eigenmap, Locality Preserving Projection, Graph Embedding, and Diffusion Map: Tutorial and Survey
• Stochastic Neighbor Embedding with Gaussian and Student-t Distributions: Tutorial and Survey
• Unified Framework for Spectral Dimensionality Reduction, Maximum Variance Unfolding, and Kernel Learning By Semidefinite Programming: Tutorial and Survey
• Efficient channel charting via phase-insensitive distance computation