Reconstruction of manifold embeddings into Euclidean spaces via intrinsic distances
arXiv:2012.13770 · doi:10.1051/cocv/2023088
Abstract
We consider the problem of reconstructing an embedding of a compact connected Riemannian manifold in a Euclidean space up to an almost isometry, given the information on intrinsic distances between points from its ``sufficiently large'' subset. This is one of the classical manifold learning problems. It happens that the most popular methods to deal with such a problem, with a long history in data science, namely, the classical Multidimensional scaling (MDS) and the Maximum variance unfolding (MVU), actually miss the point and may provide results very far from an isometry; moreover, they may even give no bi-Lipshitz embedding. We will provide an easy variational formulation of this problem, which leads to an algorithm always providing an almost isometric embedding with the distortion of original distances as small as desired (the parameter regulating the upper bound for the desired distortion is an input parameter of this algorithm).
arXiv comment21 pages, 4 figures
References in corpus (9)
- An Analysis of the t-SNE Algorithm for Data Visualization
- Manifold estimation and singular deconvolution under Hausdorff loss
- Multiscale Dictionary Learning: Non-Asymptotic Bounds and Robustness
- Manifold Approximation by Moving Least-Squares Projection (MMLS)
- Structure-adaptive manifold estimation
- Perturbation Bounds for Procrustes, Classical Scaling, and Trilateration, with Applications to Manifold Learning
- Multidimensional Scaling on Metric Measure Spaces
- Local Regularization of Noisy Point Clouds: Improved Global Geometric Estimates and Data Analysis
- Classical Multidimensional Scaling on Metric Measure Spaces