A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind Deconvolution · arXivDesk
1908.10776Aug 28, 201962 pages, 6 figures; short version accepted as a spotlight paper at NeurIPS'19 (https://papers.nips.cc/paper/8656-a-nonconvex-approach-for-exact-and-efficient-multichannel-sparse-blind-deconvolution) ; A long journal version is under revision at SIIMS
A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind Deconvolution
We study the multi-channel sparse blind deconvolution (MCS-BD) problem, whose task is to simultaneously recover a kernel a and multiple sparse inputs {xi}i=1p from their circulant convolution yi=a⊛xi
Nearby in the stack
(
i=1,⋯,p
). We formulate the task as a nonconvex optimization problem over the sphere. Under mild statistical assumptions of the data, we prove that the vanilla Riemannian gradient descent (RGD) method, with random initializations, provably recovers both the kernel
a
and the signals
{xi}i=1p
up to a signed shift ambiguity. In comparison with state-of-the-art results, our work shows significant improvements in terms of sample complexity and computational efficiency. Our theoretical results are corroborated by numerical experiments, which demonstrate superior performance of the proposed approach over the previous methods on both synthetic and real datasets.