Spotlight
A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind Deconvolution
Qing Qu · Xiao Li · Zhihui Zhu

Thu Dec 12th 04:05 -- 04:10 PM @ West Ballroom C

We study the multi-channel sparse blind deconvolution (MCS-BD) problem, whose task is to simultaneously recover a kernel $\mathbf a$ and multiple sparse inputs ${\mathbf xi}{i=1}^p$ from their circulant convolution $\mathbf yi = \mb a \circledast \mb xi $ ($i=1,\cdots,p$). 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 $\mathbf a$ and the signals ${\mathbf xi}{i=1}^p$ 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.

Author Information

Qing Qu (New York University)
Xiao Li (The Chinese University of Hong Kong)
Zhihui Zhu (Johns Hopkins University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors