Parallel transport unfolding: a connection-based manifold learning approach
From MaRDI portal
Abstract: Manifold learning offers nonlinear dimensionality reduction of high-dimensional datasets. In this paper, we bring geometry processing to bear on manifold learning by introducing a new approach based on metric connection for generating a quasi-isometric, low-dimensional mapping from a sparse and irregular sampling of an arbitrary manifold embedded in a high-dimensional space. Geodesic distances of discrete paths over the input pointset are evaluated through "parallel transport unfolding" (PTU) to offer robustness to poor sampling and arbitrary topology. Our new geometric procedure exhibits the same strong resilience to noise as one of the staples of manifold learning, the Isomap algorithm, as it also exploits all pairwise geodesic distances to compute a low-dimensional embedding. While Isomap is limited to geodesically-convex sampled domains, parallel transport unfolding does not suffer from this crippling limitation, resulting in an improved robustness to irregularity and voids in the sampling. Moreover, it involves only simple linear algebra, significantly improves the accuracy of all pairwise geodesic distance approximations, and has the same computational complexity as Isomap. Finally, we show that our connection-based distance estimation can be used for faster variants of Isomap such as L-Isomap.
Recommendations
Cites work
- A novel M-estimator for robust PCA
- An Intrinsic Dimensionality Estimator from Near-Neighbor Information
- Connectivity of the mutual k-nearest-neighbor graph in clustering and outlier detection
- Eigensolver Methods for Progressive Multidimensional Scaling of Large Data
- Finding structure with randomness: probabilistic algorithms for constructing approximate matrix decompositions
- Generalized principal component analysis
- Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data
- scientific article; zbMATH DE number 6378042 (Why is no real title available?)
- scientific article; zbMATH DE number 3686284 (Why is no real title available?)
- scientific article; zbMATH DE number 1974121 (Why is no real title available?)
- scientific article; zbMATH DE number 914851 (Why is no real title available?)
- Kinematics and differential geometry of submanifolds
- Locality-sensitive hashing scheme based on p-stable distributions
- Modern multidimensional scaling. Theory and applications.
- Nonlinear dimensionality reduction by topologically constrained isometric embedding
- Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment
- Robust kernel Isomap
- The geometry of physics. An introduction
- Vector diffusion maps and the connection Laplacian
Cited in
(8)- Fractional diffusion maps
- Generalized bounds for active subspaces
- Laplacian-optimized diffusion for semi-supervised learning
- A manifold unfolding method based on boundary constraints
- Manifold unfolding by isometric patch alignment with an application in protein structure determination
- Nonlinear level set learning for function approximation on sparse data with applications to parametric differential equations
- Nonlinear dimension reduction for functional data with application to clustering
- Supervised Manifold Learning for Functional Data
This page was built for publication: Parallel transport unfolding: a connection-based manifold learning approach
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5234527)
