Low-rank MMSE filters, Kronecker-product representation, and regularization: a new perspective
This work addresses a specific computational bottleneck in signal processing for applications like communications or imaging, but it appears incremental as it builds on known low-rank and Kronecker methods.
The paper tackles the problem of efficiently selecting regularization parameters for low-rank MMSE filters using a Kronecker-product representation, showing that this parameter is linked to rank selection and demonstrating significant gains over existing methods in simulations.
In this work, we propose a method to efficiently find the regularization parameter for low-rank MMSE filters based on a Kronecker-product representation. We show that the regularization parameter is surprisingly linked to the problem of rank selection and, thus, properly choosing it, is crucial for low-rank settings. The proposed method is validated through simulations, showing significant gains over commonly used methods.