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

11/25/2019
by   Laixi Shi, et al.
0

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 respect to the unknown filter and inputs, leading to global ambiguities of identification. 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 the 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 methods.

READ FULL TEXT

page 11

page 12

research
05/26/2018

Global Geometry of Multichannel Sparse Blind Deconvolution on the Sphere

Multichannel blind deconvolution is the problem of recovering an unknown...
research
11/20/2018

Blind Deconvolution using Modulated Inputs

This paper considers the blind deconvolution of multiple modulated signa...
research
08/28/2019

A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind Deconvolution

We study the multi-channel sparse blind deconvolution (MCS-BD) problem, ...
research
03/12/2018

Blind Identification of Invertible Graph Filters with Multiple Sparse Inputs

This paper deals with problem of blind identification of a graph filter ...
research
05/08/2023

Gaussian process deconvolution

Let us consider the deconvolution problem, that is, to recover a latent ...
research
11/05/2021

Guaranteed blind deconvolution and demixing via hierarchically sparse reconstruction

The blind deconvolution problem amounts to reconstructing both a signal ...
research
06/13/2021

Convex Sparse Blind Deconvolution

In the blind deconvolution problem, we observe the convolution of an unk...

Please sign up or login with your details

Forgot password? Click here to reset