Reviews: Multivariate Convolutional Sparse Coding for Electromagnetic Brain Signals

This work extends convolutional sparse coding to the multivariate case with a focus on multichannel EEG decomposition. This corresponds to a non-convex minimization problem and a local minimum is found via an alternating optimization. Reasonable efficient bookkeeping (precomputation of certain factors, and windowing for locally greedy coordinate descent) is used to improve scalability. The locally greedy coordinate descent cycles time windows, but computes a greedy coordinate descent within each window. As spatial patterns are essential for understanding EEG, this multivariate extension is an important contribution.