New analysis of manifold embeddings and signal recovery from compressive measurements
From MaRDI portal
Publication:2347898
compressive sensingdimensionality reductionmanifold embeddingsmanifoldsparameter estimationrandom projectionssignal recovery
Higher-dimensional and -codimensional surfaces in Euclidean and related (n)-spaces (53A07) Estimation in multivariate analysis (62H12) Coding and information theory (compaction, compression, models of communication, encoding schemes, etc.) (aspects in computer science) (68P30) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Source coding (94A29)
Abstract: Compressive Sensing (CS) exploits the surprising fact that the information contained in a sparse signal can be preserved in a small number of compressive, often random linear measurements of that signal. Strong theoretical guarantees have been established concerning the embedding of a sparse signal family under a random measurement operator and on the accuracy to which sparse signals can be recovered from noisy compressive measurements. In this paper, we address similar questions in the context of a different modeling framework. Instead of sparse models, we focus on the broad class of manifold models, which can arise in both parametric and non-parametric signal families. Using tools from the theory of empirical processes, we improve upon previous results concerning the embedding of low-dimensional manifolds under random measurement operators. We also establish both deterministic and probabilistic instance-optimal bounds in for manifold-based signal recovery and parameter estimation from noisy compressive measurements. In line with analogous results for sparsity-based CS, we conclude that much stronger bounds are possible in the probabilistic setting. Our work supports the growing evidence that manifold-based models can be used with high accuracy in compressive signal processing.
Recommendations
- On recovery guarantees for one-bit compressed sensing on manifolds
- Compressive sensing with redundant dictionaries and structured measurements
- Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
- Compressed Sensing and Redundant Dictionaries
- From compression to compressed sensing
Cites work
- A simple proof of the restricted isometry property for random matrices
- Adaptive estimation of a quadratic functional by model selection.
- Analysis of Orthogonal Matching Pursuit Using the Restricted Isometry Property
- Approximation of points on low-dimensional manifolds via random linear projections
- Beyond Nyquist: Efficient Sampling of Sparse Bandlimited Signals
- Breakdown of equivalence between the minimal ^1-norm solution and the sparsest solution
- Compressed sensing
- Compressed sensing and best \(k\)-term approximation
- Compressive sensing and structured random matrices
- Compressive Sensing on Manifolds Using a Nonparametric Mixture of Factor Analyzers: Algorithm and Performance Bounds
- CoSaMP: Iterative signal recovery from incomplete and inaccurate samples
- Curvature Measures
- Decoding by Linear Programming
- Distance preserving embeddings for general n-dimensional manifolds
- Error and Perturbation Bounds for Subspaces Associated with Certain Eigenvalue Problems
- Finding the homology of submanifolds with high confidence from random samples
- scientific article; zbMATH DE number 5485456 (Why is no real title available?)
- scientific article; zbMATH DE number 1775450 (Why is no real title available?)
- Image manifolds which are isometric to Euclidean space
- Instance-optimality in probability with an \(\ell _1\)-minimization decoder
- Joint Manifolds for Data Fusion
- Matched Filtering From Limited Frequency Samples
- Measurement Bounds for Sparse Signal Ensembles via Graphical Models
- Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
- NIST handbook of mathematical functions
- On sparse reconstruction from Fourier and Gaussian measurements
- Probability in Banach spaces. Isoperimetry and processes
- Random projections of smooth manifolds
- Restricted isometries for partial random circulant matrices
- Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
- Signal Recovery on Incoherent Manifolds
- Sparse channel separation using random probes
- Stable signal recovery from incomplete and inaccurate measurements
- The Generic Chaining
- The restricted isometry property and its implications for compressed sensing
- The Whitney reduction network: A method for computing autoassociative graphs
- Tighter bounds for random projections of manifolds
Cited in
(16)- MRA contextual-recovery extension of smooth functions on manifolds
- Stable recovery of low-dimensional cones in Hilbert spaces: one RIP to rule them all
- On recovery guarantees for one-bit compressed sensing on manifolds
- Compressive statistical learning with random feature moments
- Quantized compressed sensing: a survey
- Compressive Sensing on Manifolds Using a Nonparametric Mixture of Factor Analyzers: Algorithm and Performance Bounds
- Representation and coding of signal geometry
- Time for dithering: fast and quantized random embeddings via the restricted isometry property
- Dimensionality reduction with subgaussian matrices: a unified theory
- Adaptive geometric multiscale approximations for intrinsically low-dimensional data
- Endpoint results for Fourier integral operators on noncompact symmetric spaces
- What happens to a manifold under a bi-Lipschitz map?
- Lower bounds on the low-distortion embedding dimension of submanifolds of \(\mathbb{R}^n\)
- On fast Johnson-Lindenstrauss embeddings of compact submanifolds of \(\mathbb{R}^N\) with boundary
- Low dimensional approximation and generalization of multivariate functions on smooth manifolds using deep ReLU neural networks
- Rigorous restricted isometry property of low-dimensional subspaces
This page was built for publication: New analysis of manifold embeddings and signal recovery from compressive measurements
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2347898)
