Subspace Least Squares Multidimensional Scaling

DOI10.1007/978-3-319-58771-4_54zbMATH Open1489.68318arXiv1709.03484OpenAlexW2614356504MaRDI QIDQ5864047FDOQ5864047

Authors: Amit Boyarski, Alex M. Bronstein, Michael M. Bronstein 

Publication date: 3 June 2022

Published in: Lecture Notes in Computer Science (Search for Journal in Brave)

Abstract: Multidimensional Scaling (MDS) is one of the most popular methods for dimensionality reduction and visualization of high dimensional data. Apart from these tasks, it also found applications in the field of geometry processing for the analysis and reconstruction of non-rigid shapes. In this regard, MDS can be thought of as a extit{shape from metric} algorithm, consisting of finding a configuration of points in the Euclidean space that realize, as isometrically as possible, some given distance structure. In the present work we cast the least squares variant of MDS (LS-MDS) in the spectral domain. This uncovers a multiresolution property of distance scaling which speeds up the optimization by a significant amount, while producing comparable, and sometimes even better, embeddings.

Full work available at URL: https://arxiv.org/abs/1709.03484

Recommendations

• Publication:4887371
• Spectral multidimensional scaling
• Dimensionality-reduced subspace clustering
• Subspace Procrustes analysis
• Dimension reduction subspace with multivariate responses
• Correlation-based multidimensional scaling for unsupervised subspace learning
• Sparsity-Exploiting Robust Multidimensional Scaling
• scientific article; zbMATH DE number 7156497
• On principal subspace analysis

zbMATH Keywords

multidimensional scalingmajorizationcanonical formsmulti-resolutionspectral regularizationSMACOF

Mathematics Subject Classification ID

Computer graphics; computational geometry (digital and algorithmic aspects) (68U05) Machine vision and scene understanding (68T45)

Cited In (20)

• Cross-Gramian-based dominant subspaces
• Multidimensional scaling on metric measure spaces
• Title not available (Why is that?)
• Stress functions for nonlinear dimension reduction, proximity analysis, and graph drawing
• Rigid transformations for stabilized lower dimensional space to support subsurface uncertainty quantification and interpretation
• Scale Space and PDE Methods in Computer Vision
• Geometric multidimensional scaling: a new approach for data dimensionality reduction
• Multi-dimensional scaling from \(K\)-nearest neighbourhood distances
• A globally convergent inertial first-order optimization method for multidimensional scaling
• Geometric multidimensional scaling: efficient approach for data dimensionality reduction
• Regularized multidimensional scaling with radial basis functions
• Horseshoes in multidimensional scaling and local kernel methods
• Landmark MDS ensemble
• Multigrid multidimensional scaling
• Uncovering the Euclidean Geometry of Data
• Spectral multidimensional scaling
• Procrustes analysis of truncated least squares multidimensional scaling
• Correlation-based multidimensional scaling for unsupervised subspace learning
• Multidimensional scaling of noisy high dimensional data
• Least squares metric, unidimensional scaling of multivariate linear models

This page was built for publication: Subspace Least Squares Multidimensional Scaling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5864047)