Approximately-isometric diffusion maps

DOI10.1016/J.ACHA.2016.10.003zbMATH Open1391.68096arXiv1511.06208OpenAlexW4206927375WikidataQ110233659 ScholiaQ110233659MaRDI QIDQ723009FDOQ723009

Moshe Salhov, Amir Averbuch, Guy Wolf, Amit Bermanis

Publication date: 30 July 2018

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Abstract: Diffusion Maps framework is a kernel based method for manifold learning and data analysis that defines diffusion similarities by imposing a Markovian process on the given dataset. Analysis by this process uncovers the intrinsic geometric structures in the data. Recently, it was suggested to replace the standard kernel by a measure-based kernel that incorporates information about the density of the data. Thus, the manifold assumption is replaced by a more general measure-based assumption. The measure-based diffusion kernel incorporates two separate independent representations. The first determines a measure that correlates with a density that represents normal behaviors and patterns in the data. The second consists of the analyzed multidimensional data points. In this paper, we present a representation framework for data analysis of datasets that is based on a closed-form decomposition of the measure-based kernel. The proposed representation preserves pairwise diffusion distances that does not depend on the data size while being invariant to scale. For a stationary data, no out-of-sample extension is needed for embedding newly arrived data points in the representation space. Several aspects of the presented methodology are demonstrated on analytically generated data.

Full work available at URL: https://arxiv.org/abs/1511.06208

Recommendations

• Diffusion-based kernel methods on Euclidean metric measure spaces
• Diffusion maps
• Approximately-isometric diffusion maps
• scientific article; zbMATH DE number 5263135
• A review of analysis of and on data sets based on diffusion on graphs and manifolds

zbMATH Keywords

dimensionality reductionmanifold learningdiffusion mapskernel PCAdiffusion distancedistance preservation

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Computing a Trust Region Step
• Diffusion maps
• Title not available (Why is that?)
• Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Estimating the components of a mixture of normal distributions
• Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Title not available (Why is that?)
• Title not available (Why is that?)
• Hierarchical data organization, clustering and denoising via localized diffusion folders
• Parametrization of Linear Systems Using Diffusion Kernels
• Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment
• Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data
• Multiscale data sampling and function extension
• Diffusion-based kernel methods on Euclidean metric measure spaces
• Audio-Visual Group Recognition Using Diffusion Maps
• Lanczos Algorithms for Large Symmetric Eigenvalue Computations
• Measure-based diffusion grid construction and high-dimensional data discretization
• A Spectral Technique for Coloring Random 3-Colorable Graphs
• Recent advances in trust region algorithms
• Computing Optimal Locally Constrained Steps
• Efficient graph-based image segmentation
• Newton’s Method with a Model Trust Region Modification
• Fast computation of low rank matrix approximations
• Maximization by Quadratic Hill-Climbing
• Graph Coloring Using Eigenvalue Decomposition
• Cover-based bounds on the numerical rank of Gaussian kernels

Cited In (11)

• Diffusion maps
• Diffusion-based kernel methods on Euclidean metric measure spaces
• Orientability and diffusion maps
• Diffusion representation for asymmetric kernels
• Diffusion maps for changing data
• Geometric component analysis and its applications to data analysis
• Spectral Convergence of Diffusion Maps: Improved Error Bounds and an Alternative Normalization
• Double diffusion maps and their latent harmonics for scientific computations in latent space
• Scalability and robustness of spectral embedding: landmark diffusion is all you need
• Title not available (Why is that?)
• Diffusion generated motion using signed distance functions

Uses Software

• GQTPAR

This page was built for publication: Approximately-isometric diffusion maps

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q723009)