Stable separation and super-resolution of mixture models

DOI10.1016/J.ACHA.2017.03.003MaRDI QIDQ1990966zbMATH OpenOpenAlexFDO

Authors Yuejie Chi, Yuan-Xin Li

Publication date 29 October 2018

Published in Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1506.07347

zbMATH Keywords

parameter estimationmixture modelssuper-resolutionatomic norm minimization

Mathematics Subject Classification ID

Convex programming (90C25) Applications of mathematical programming (90C90) Inequalities; stochastic orderings (60E15) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Abstract: We consider simultaneously identifying the membership and locations of point sources that are convolved with different band-limited point spread functions, from the observation of their superpositions. This problem arises in three-dimensional super-resolution single-molecule imaging, neural spike sorting, multi-user channel identification, among other applications. We propose a novel algorithm, based on convex programming, and establish its near-optimal performance guarantee for exact recovery in the noise-free setting by exploiting the spectral sparsity of the point source models as well as the incoherence between point spread functions. Furthermore, robustness of the recovery algorithm in the presence of bounded noise is also established. Numerical examples are provided to demonstrate the effectiveness of the proposed approach.

Recommendations

• Stable super-resolution of images: theoretical study
• Super-resolution of point sources via convex programming
• Super-resolution of positive sources: the discrete setup
• Super-resolution from noisy data
• Multivariate super-resolution without separation

Cites work

• A review of methods for spike sorting: the detection and classification of neural action potentials
• Atomic Norm Denoising With Applications to Line Spectral Estimation
• Compressed Sensing Off the Grid
• Compressive Two-Dimensional Harmonic Retrieval via Atomic Norm Minimization
• Exact Recoverability From Dense Corrupted Observations via $\ell _{1}$-Minimization
• Inequalities of A. Markoff and S. Bernstein for polynomials and related functions
• Introduction to spectral analysis
• Matrix pencil method for estimating parameters of exponentially damped/undamped sinusoids in noise
• Near Minimax Line Spectral Estimation
• Off-the-Grid Line Spectrum Denoising and Estimation With Multiple Measurement Vectors
• On the detection of singularities of a periodic function
• Parametric deconvolution of positive spike trains.
• Probability Inequalities for Sums of Bounded Random Variables
• Robust Spectral Compressed Sensing via Structured Matrix Completion
• Robust principal component analysis?
• Sensitivity to Basis Mismatch in Compressed Sensing
• Super-resolution from noisy data
• Super-resolution of point sources via convex programming
• The convex geometry of linear inverse problems
• Towards a Mathematical Theory of Super‐resolution
• User-friendly tail bounds for sums of random matrices

Cited in

(4)

• Supermix: sparse regularization for mixtures
• Multi-kernel unmixing and super-resolution using the modified matrix pencil method
• A note on spike localization for line spectrum estimation
• A unified method for super-resolution recovery and real exponential-sum separation

Describes a project that uses

Uses Software

• CVX

This page was built for publication: Stable separation and super-resolution of mixture models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1990966)