Random projections of smooth manifolds

DOI10.1007/s10208-007-9011-zzbMath1172.53005OpenAlexW1986736933WikidataQ125259994 ScholiaQ125259994MaRDI QIDQ1029551

Richard G. Baraniuk, Michael B. Wakin

Publication date: 13 July 2009

Published in: Foundations of Computational Mathematics (Search for Journal in Brave)

Full work available at URL: http://hdl.handle.net/1911/19724

zbMATH Keywords

manifoldsdimensionality reductionrandom projectionsparsitymanifold learningcompressed sensingJohnson-Lindenstrauss lemma

Mathematics Subject Classification ID

Multivariate analysis (62H99) Learning and adaptive systems in artificial intelligence (68T05) Higher-dimensional and -codimensional surfaces in Euclidean and related (n)-spaces (53A07) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Coding and information theory (compaction, compression, models of communication, encoding schemes, etc.) (aspects in computer science) (68P30) Source coding (94A29) Probabilistic methods, stochastic differential equations (65C99)

Related Items

Kernel Approximation on Algebraic Varieties, Dimension reduction and construction of feature space for image pattern recognition, Inverse problems on low-dimensional manifolds, Sparse Model Uncertainties in Compressed Sensing with Application to Convolutions and Sporadic Communication, Multiscale geometric methods for data sets. I: Multiscale SVD, noise and curvature., Generalizing CoSaMP to signals from a union of low dimensional linear subspaces, The Discovery of Dynamics via Linear Multistep Methods and Deep Learning: Error Estimation, Algebraic compressed sensing, A deep network construction that adapts to intrinsic dimensionality beyond the domain, Neural network approximation of continuous functions in high dimensions with applications to inverse problems, Multi-scale geometric methods for data sets. II: Geometric multi-resolution analysis, Reconstruction of manifold embeddings into Euclidean spaces via intrinsic distances, On fast Johnson-Lindenstrauss embeddings of compact submanifolds of \(\mathbb{R}^N\) with boundary, Modewise operators, the tensor restricted isometry property, and low-rank tensor recovery, Deep nonparametric regression on approximate manifolds: nonasymptotic error bounds with polynomial prefactors, Representation and coding of signal geometry, Robustness properties of dimensionality reduction with Gaussian random matrices, Manifold estimation and singular deconvolution under Hausdorff loss, Statistical mechanics of complex neural systems and high dimensional data, Toward a unified theory of sparse dimensionality reduction in Euclidean space, Dimensionality reduction with subgaussian matrices: a unified theory, Persistent homology for low-complexity models, Deep Network Approximation Characterized by Number of Neurons, What happens to a manifold under a bi-Lipschitz map?, Spectral compressive sensing, Two-dimensional random projection, Testing the manifold hypothesis, On recovery guarantees for one-bit compressed sensing on manifolds, The Bottleneck Degree of Algebraic Varieties, CoverBLIP: accelerated and scalable iterative matched-filtering for magnetic resonance fingerprint reconstruction*, Dimensionality reduction for \(k\)-distance applied to persistent homology, Random projections of smooth manifolds, Manifold reconstruction and denoising from scattered data in high dimension, Sensitivity of low-rank matrix recovery, New analysis of manifold embeddings and signal recovery from compressive measurements, Sparse control of alignment models in high dimension

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• On the stability of the basis pursuit in the presence of noise
• Random projections of smooth manifolds
• A simple proof of the restricted isometry property for random matrices
• The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
• Finding the homology of submanifolds with high confidence from random samples
• Diffusion wavelets
• High-dimensional centrally symmetric polytopes with neighborliness proportional to dimension
• Image manifolds which are isometric to Euclidean space
• The Whitney Reduction Network: A Method for Computing Autoassociative Graphs
• Counting faces of randomly projected polytopes when the projection radically lowers dimension
• Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
• Decoding by Linear Programming
• Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
• Signal Reconstruction From Noisy Random Projections
• Nearest-neighbor-preserving embeddings
• A New Approach to Dimensionality Reduction: Theory and Algorithms
• Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment
• An elementary proof of a theorem of Johnson and Lindenstrauss
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Geodesic Entropic Graphs for Dimension and Entropy Estimation in Manifold Learning
• Neighborliness of randomly projected simplices in high dimensions
• Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data
• For most large underdetermined systems of linear equations the minimal 𝓁₁‐norm solution is also the sparsest solution
• Multiscale Representations for Manifold-Valued Data
• Stable signal recovery from incomplete and inaccurate measurements
• Compressed sensing