Iterative Regularization with k-support Norm: An Important Complement to Sparse Recovery

arXiv:2401.05394v3 Announce Type: replace-cross
Abstract: Sparse recovery is ubiquitous in machine learning and signal processing. Due to the NP-hard nature of sparse recovery, existing methods are known to suffer either from restrictive (or even unknown) applicability conditions, or high computational cost. Recently, iterative regularization methods have emerged as a promising fast approach because they can achieve sparse recovery in one pass through early stopping, rather than the tedious grid-search used in the traditional methods. However, most of those iterative methods …

abstract arxiv computational cost cs.lg eess.sp iterative machine machine learning math.oc nature norm np-hard processing recovery regularization restrictive signal stat.ml support type