Multiscale geometric methods for data sets. I: Multiscale SVD, noise and curvature.
From MaRDI portal
Publication:2402490
DOI10.1016/j.acha.2015.09.009OpenAlexW1519654970MaRDI QIDQ2402490
Lorenzo Rosasco, Anna V. Little, Mauro Maggioni
Publication date: 7 September 2017
Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)
Full work available at URL: http://hdl.handle.net/1721.1/72597
probability distributionsmultiscale analysisgeometric measure theorymanifold learningcovariance matrix estimationintrinsic dimension estimationpoint cloud datamultiscale singular values
Factor analysis and principal components; correspondence analysis (62H25) Probability distributions: general theory (60E05)
Related Items (20)
IAN: Iterated Adaptive Neighborhoods for Manifold Learning and Dimensionality Estimation ⋮ A Maximum Principle Argument for the Uniform Convergence of Graph Laplacian Regressors ⋮ Adaptive Geometric Multiscale Approximations for Intrinsically Low-dimensional Data ⋮ Manifold Learning and Nonlinear Homogenization ⋮ Tangent estimation from point samples ⋮ Unnamed Item ⋮ A machine learning approach to optimal Tikhonov regularization I: Affine manifolds ⋮ Multi-scale geometric methods for data sets. II: Geometric multi-resolution analysis ⋮ Wassmap: Wasserstein Isometric Mapping for Image Manifold Learning ⋮ Nonlinear model reduction for slow-fast stochastic systems near unknown invariant manifolds ⋮ Approximation of functions over manifolds: a moving least-squares approach ⋮ An analyst's traveling salesman theorem for sets of dimension larger than one ⋮ Estimating covariance and precision matrices along subspaces ⋮ ATLAS: A Geometric Approach to Learning High-Dimensional Stochastic Systems Near Manifolds ⋮ Connecting dots: from local covariance to empirical intrinsic geometry and locally linear embedding ⋮ Efficient Weingarten map and curvature estimation on manifolds ⋮ Implicit manifold reconstruction ⋮ Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance ⋮ Unnamed Item ⋮ A Tale of Two Bases: Local-Nonlocal Regularization on Image Patches with Convolution Framelets
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Multi-scale geometric methods for data sets. II: Geometric multi-resolution analysis
- How close is the sample covariance matrix to the actual covariance matrix?
- Rectifiable sets and the traveling salesman problem
- Translated Poisson mixture model for stratification learning
- Finite sample approximation results for principal component analysis: A matrix perturbation approach
- Intrinsic dimension estimation of manifolds by incising balls
- Random projections of smooth manifolds
- Measuring the strangeness of strange attractors
- The traveling salesman problem and harmonic analysis
- Random vectors in the isotropic position
- Consistency of the Takens estimator for the correlation dimension
- Empirical geometry of multivariate data: a deconvolution approach.
- On the distribution of the largest eigenvalue in principal components analysis
- Optimum bounds for the distributions of martingales in Banach spaces
- Hybrid linear modeling via local best-fit flats
- Topology from time series
- On the empirical distribution of eigenvalues of large dimensional information-plus-noise-type matrices
- Regularized estimation of large covariance matrices
- Finding the homology of submanifolds with high confidence from random samples
- Diffusion maps
- Eigenvalues of large sample covariance matrices of spiked population models
- Manifold parametrizations by eigenfunctions of the Laplacian and heat kernels
- Extensions of Lipschitz mappings into a Hilbert space
- Local adaptive Galerkin bases for large-dimensional dynamical systems
- A Randomized Algorithm for Principal Component Analysis
- Smallest singular value of a random rectangular matrix
- Topological dimension and local coordinates from time series data
- Compressive Sensing on Manifolds Using a Nonparametric Mixture of Factor Analyzers: Algorithm and Performance Bounds
- Geometric diffusions as a tool for harmonic analysis and structure definition of data: Diffusion maps
- Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment
- Uniform rectifiability and quasiminimizing sets of arbitrary codimension
- Approximation of points on low-dimensional manifolds via random linear projections
- Geodesic Entropic Graphs for Dimension and Entropy Estimation in Manifold Learning
- Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data
- Fast Construction of Nets in Low-Dimensional Metrics and Their Applications
- Learning Theory
- A Measure of Asymptotic Efficiency for Tests of a Hypothesis Based on the sum of Observations
- Intrinsic dimension estimation of data: An approach based on Grassberger-Procaccia's algorithm
This page was built for publication: Multiscale geometric methods for data sets. I: Multiscale SVD, noise and curvature.
