Minimax manifold estimation
From MaRDI portal
Abstract: We find the minimax rate of convergence in Hausdorff distance for estimating a manifold M of dimension d embedded in R^D given a noisy sample from the manifold. We assume that the manifold satisfies a smoothness condition and that the noise distribution has compact support. We show that the optimal rate of convergence is n^{-2/(2+d)}. Thus, the minimax rate depends only on the dimension of the manifold, not on the dimension of the space in which M is embedded.
Recommendations
- Tight minimax rates for manifold estimation under Hausdorff loss
- Minimax rates for estimating the dimension of a manifold
- Minimax adaptive estimation in manifold inference
- Nonasymptotic rates for manifold, tangent space and curvature estimation
- Manifold estimation and singular deconvolution under Hausdorff loss
Cited in
(40)- Statistical analysis and parameter selection for Mapper
- Randomized Wasserstein barycenter computation: resampling with statistical guarantees
- Reconstruction of a Riemannian manifold from noisy intrinsic distances
- scientific article; zbMATH DE number 1167661 (Why is no real title available?)
- Density estimation on an unknown submanifold
- Optimal reach estimation and metric learning
- Testing the manifold hypothesis
- Estimating the reach of a manifold
- Deep nonparametric estimation of intrinsic data structures by chart autoencoders: generalization error and robustness
- On boundary detection
- Universally consistent estimation of the reach
- Estimating the reach of a manifold via its convexity defect function
- Nonasymptotic rates for manifold, tangent space and curvature estimation
- scientific article; zbMATH DE number 7306873 (Why is no real title available?)
- Convergence rate for the \(\lambda \)-medial-axis estimation under regularity conditions
- The bottleneck degree of algebraic varieties
- Manifold estimation and singular deconvolution under Hausdorff loss
- Tangent space and dimension estimation with the Wasserstein distance
- IAN: Iterated Adaptive Neighborhoods for Manifold Learning and Dimensionality Estimation
- Learning the geometric structure of manifolds with singularities using the tensor voting graph
- Measure estimation on manifolds: an optimal transport approach
- Local regularization of noisy point clouds: improved global geometric estimates and data analysis
- scientific article; zbMATH DE number 6999890 (Why is no real title available?)
- Data analysis from empirical moments and the Christoffel function
- Level set and density estimation on manifolds
- Stability and minimax optimality of tangential Delaunay complexes for manifold reconstruction
- Asymptotics and optimal bandwidth for nonparametric estimation of density level sets
- Minimax rates for estimating the dimension of a manifold
- Minimax boundary estimation and estimation with boundary
- Minimax rate of distribution estimation on unknown submanifolds under adversarial losses
- A non-classical parameterization for density estimation using sample moments
- scientific article; zbMATH DE number 7625193 (Why is no real title available?)
- Tight minimax rates for manifold estimation under Hausdorff loss
- Minimax fast rates for discriminant analysis with errors in variables
- Nonparametric ridge estimation
- Minimax adaptive estimation in manifold inference
- A deep network construction that adapts to intrinsic dimensionality beyond the domain
- Remember the curse of dimensionality: the case of goodness-of-fit testing in arbitrary dimension
- Asymptotic theory for density ridges
- Adversarial manifold estimation
This page was built for publication: Minimax manifold estimation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5405161)
