Manifold Gradient Descent Solves Multi-Channel Sparse Blind Deconvolution Provably and Efficiently

DOI10.1109/TIT.2021.3075148MaRDI QIDQ5001827zbMATH OpenOpenAlexFDO

Authors Laixi Shi, Yuejie Chi

Publication date 23 July 2021

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1911.11167

zbMATH Keywords

convolutional sparse codingnonconvex optimization

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Methods of reduced gradient type (90C52) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Abstract: Multi-channel sparse blind deconvolution, or convolutional sparse coding, refers to the problem of learning an unknown filter by observing its circulant convolutions with multiple input signals that are sparse. This problem finds numerous applications in signal processing, computer vision, and inverse problems. However, it is challenging to learn the filter efficiently due to the bilinear structure of the observations with the respect to the unknown filter and inputs, as well as the sparsity constraint. In this paper, we propose a novel approach based on nonconvex optimization over the sphere manifold by minimizing a smooth surrogate of the sparsity-promoting loss function. It is demonstrated that manifold gradient descent with random initializations will provably recover the filter, up to scaling and shift ambiguity, as soon as the number of observations is sufficiently large under an appropriate random data model. Numerical experiments are provided to illustrate the performance of the proposed method with comparisons to existing ones.

Recommendations

• Exact Recovery of Multichannel Sparse Blind Deconvolution via Gradient Descent
• Regularized gradient descent: a non-convex recipe for fast joint blind deconvolution and demixing
• Blind deconvolution by a steepest descent algorithm on a quotient manifold
• Sparse blind deconvolution and demixing through \(\ell_{1,2}\)-minimization
• Robust Multichannel Blind Deconvolution via Fast Alternating Minimization
• Manifold estimation and singular deconvolution under Hausdorff loss
• Rapid, robust, and reliable blind deconvolution via nonconvex optimization
• Leveraging Diversity and Sparsity in Blind Deconvolution
• Multichannel Sparse Blind Deconvolution on the Sphere

Cited in

(4)

• Exact Recovery of Multichannel Sparse Blind Deconvolution via Gradient Descent
• Convex and Nonconvex Optimization Are Both Minimax-Optimal for Noisy Blind Deconvolution Under Random Designs
• Recent Theoretical Advances in Non-Convex Optimization
• The power of preconditioning in overparameterized low-rank matrix sensing

This page was built for publication: Manifold Gradient Descent Solves Multi-Channel Sparse Blind Deconvolution Provably and Efficiently

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5001827)