An axiomatic approach to intrinsic dimension of a dataset
From MaRDI portal
Publication:1931997
DOI10.1016/j.neunet.2007.12.030zbMath1254.68102arXiv0712.2063OpenAlexW1489992831WikidataQ51895521 ScholiaQ51895521MaRDI QIDQ1931997
Publication date: 17 January 2013
Published in: Neural Networks (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/0712.2063
featuresconcentration of measurecurse of dimensionalityGromov distancehigh-dimensional noiseintrinsic dimension of datasetsrandom sample of a manifoldspace with metric and measure
Related Items (9)
Is the \(k\)-NN classifier in high dimensions affected by the curse of dimensionality? ⋮ Anderson relaxation test for intrinsic dimension selection in model-based clustering ⋮ Intrinsic dimension estimation: relevant techniques and a benchmark framework ⋮ Lower bounds on performance of metric tree indexing schemes for exact similarity search in high dimensions ⋮ Indexability, concentration, and VC theory ⋮ Dimension estimation using weighted correlation dimension method ⋮ Intrinsic dimension estimation: advances and open problems ⋮ Prequential analysis of complex data with adaptive model reselection ⋮ Intrinsic dimension of geometric data sets
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- On the geometry of similarity search: dimensionality curse and concentration of measure
- Asymptotic theory of finite dimensional normed spaces. With an appendix by M. Gromov: Isoperimetric inequalities in Riemannian manifolds
- Mass transportation problems. Vol. 1: Theory. Vol. 2: Applications
- Neural Network Learning
- Geodesic Entropic Graphs for Dimension and Entropy Estimation in Manifold Learning
- Metric structures for Riemannian and non-Riemannian spaces. Transl. from the French by Sean Michael Bates. With appendices by M. Katz, P. Pansu, and S. Semmes. Edited by J. LaFontaine and P. Pansu
This page was built for publication: An axiomatic approach to intrinsic dimension of a dataset