Convex Recovery of a Structured Signal from Independent Random Linear Measurements
From MaRDI portal
Abstract: This chapter develops a theoretical analysis of the convex programming method for recovering a structured signal from independent random linear measurements. This technique delivers bounds for the sampling complexity that are similar with recent results for standard Gaussian measurements, but the argument applies to a much wider class of measurement ensembles. To demonstrate the power of this approach, the paper presents a short analysis of phase retrieval by trace-norm minimization. The key technical tool is a framework, due to Mendelson and coauthors, for bounding a nonnegative empirical process.
Recommendations
- Structured Signal Recovery From Non-Linear and Heavy-Tailed Measurements
- Signal Recovery With Certain Involved Convex Data-Fidelity Constraints
- Stable Recovery of Structured Signals From Corrupted Sub-Gaussian Measurements
- Near-optimal matrix recovery from random linear measurements
- Structured Signal Recovery From Quadratic Measurements: Breaking Sample Complexity Barriers via Nonconvex Optimization
- Sparse signal recovery from quadratic measurements via convex programming
- Recovery From Linear Measurements With Complexity-Matching Universal Signal Estimation
- Convex feasibility modeling and projection methods for sparse signal recovery
- Recovering structured signals in noise: least-squares meets compressed sensing
- Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit
Cites work
- Characterization of the subdifferential of some matrix norms
- Concentration inequalities. A nonasymptotic theory of independence
- Convex Analysis
- Corrupted Sensing: Novel Guarantees for Separating Structured Signals
- Empirical processes with a bounded \(\psi_1\) diameter
- scientific article; zbMATH DE number 49190 (Why is no real title available?)
- scientific article; zbMATH DE number 194093 (Why is no real title available?)
- scientific article; zbMATH DE number 729736 (Why is no real title available?)
- Living on the edge: phase transitions in convex programs with random data
- On general minimax theorems
- On sparse reconstruction from Fourier and Gaussian measurements
- Painless reconstruction from magnitudes of frame coefficients
- Phaselift: exact and stable signal recovery from magnitude measurements via convex programming
- Reconstruction and subgaussian operators in asymptotic geometric analysis
- Recovering Low-Rank Matrices From Few Coefficients in Any Basis
- Some inequalities for Gaussian processes and applications
- The convex geometry of linear inverse problems
- The masked sample covariance estimator: an analysis using matrix concentration inequalities
Cited in
(48)- A note on computing the smallest conic singular value
- Simplicial faces of the set of correlation matrices
- Sparse space-time models: concentration inequalities and Lasso
- Phase retrieval with PhaseLift algorithm
- The distribution of the Lasso: uniform control over sparse balls and adaptive parameter tuning
- Proof methods for robust low-rank matrix recovery
- Bias versus non-convexity in compressed sensing
- Implicit regularization in nonconvex statistical estimation: gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution
- Complex phase retrieval from subgaussian measurements
- Sharp oracle inequalities for low-complexity priors
- Solving equations of random convex functions via anchored regression
- Compressed sensing for finite-valued signals
- Consistency of \(\ell_1\) recovery from noisy deterministic measurements
- \(\ell^1\)-analysis minimization and generalized (co-)sparsity: when does recovery succeed?
- Generic error bounds for the generalized Lasso with sub-exponential data
- Estimation in high dimensions: a geometric perspective
- Low rank matrix recovery from rank one measurements
- Convex Regularizations for the Simultaneous Recording of Room Impulse Responses
- Signal Recovery With Certain Involved Convex Data-Fidelity Constraints
- Near-optimal estimation of simultaneously sparse and low-rank matrices from nested linear measurements
- Stable low-rank matrix recovery via null space properties
- scientific article; zbMATH DE number 782061 (Why is no real title available?)
- Structured random measurements in signal processing
- Low-Rank Matrix Estimation from Rank-One Projections by Unlifted Convex Optimization
- Robust width: a characterization of uniformly stable and robust compressed sensing
- Fast convex pruning of deep neural networks
- Norm and trace estimation with random rank-one vectors
- Simultaneous phase retrieval and blind deconvolution via convex programming
- Stable Recovery of Structured Signals From Corrupted Sub-Gaussian Measurements
- Linear convergence of Frank-Wolfe for rank-one matrix recovery without strong convexity
- Robust sensing of low-rank matrices with non-orthogonal sparse decomposition
- A unified approach to uniform signal recovery from nonlinear observations
- Sampling rates for ^1-synthesis
- Noisy linear inverse problems under convex constraints: exact risk asymptotics in high dimensions
- The Lasso with general Gaussian designs with applications to hypothesis testing
- Performance bounds of the intensity-based estimators for noisy phase retrieval
- A Unified Recovery of Structured Signals Using Atomic Norm
- Cardinality-constrained structured data-fitting problems
- Critical values of multilinear Forms under conic constraints
- Robust sparse recovery with sparse Bernoulli matrices via expanders
- Theory and fast learned solver for ^1-TV regularization
- Low-rank matrix recovery via rank one tight frame measurements
- Robust outlier bound condition to phase retrieval with adversarial sparse outliers
- On solution uniqueness and robust recovery for sparse regularization with a gauge: from dual point of view
- Convergence and recovery guarantees of unsupervised neural networks for inverse problems
- Letter to the editor. Stable low-rank matrix recovery from 3-designs
- Preserving injectivity under subgaussian mappings and its application to compressed sensing
- BranchHull: convex bilinear inversion from the entrywise product of signals with known signs
This page was built for publication: Convex Recovery of a Structured Signal from Independent Random Linear Measurements
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2799918)
