Maximum Discrepancy Generative Regularization and Non-Negative Matrix Factorization for Single Channel Source Separation

arXiv:2404.15296v1 Announce Type: cross
Abstract: The idea of adversarial learning of regularization functionals has recently been introduced in the wider context of inverse problems. The intuition behind this method is the realization that it is not only necessary to learn the basic features that make up a class of signals one wants to represent, but also, or even more so, which features to avoid in the representation. In this paper, we will apply this approach to the training of generative …

abstract adversarial adversarial learning arxiv basic context cs.lg cs.na eess.sp factorization features generative intuition learn math.na matrix maximum negative regularization stat.ml type