Reconstruction of manifold embeddings into Euclidean spaces via intrinsic distances
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2020
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914651605827584 |
|---|---|
| author | Puchkin, Nikita Spokoiny, Vladimir Stepanov, Eugene Trevisan, Dario |
| author_facet | Puchkin, Nikita Spokoiny, Vladimir Stepanov, Eugene Trevisan, Dario |
| contents | 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). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2012_13770 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | Reconstruction of manifold embeddings into Euclidean spaces via intrinsic distances Puchkin, Nikita Spokoiny, Vladimir Stepanov, Eugene Trevisan, Dario Optimization and Control Metric Geometry 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). |
| title | Reconstruction of manifold embeddings into Euclidean spaces via intrinsic distances |
| topic | Optimization and Control Metric Geometry |
| url | https://arxiv.org/abs/2012.13770 |