Generalized Cauchy-Schwarz Divergence and Its Deep Learning Applications

arXiv:2405.04061v1 Announce Type: new
Abstract: Divergence measures play a central role in machine learning and become increasingly essential in deep learning. However, valid and computationally efficient divergence measures for multiple (more than two) distributions are scarcely investigated. This becomes particularly crucial in areas where the simultaneous management of multiple distributions is both unavoidable and essential. Examples include clustering, multi-source domain adaptation or generalization, and multi-view learning, among others. Although calculating the mean of pairwise distances between any two distributions serves …

abstract applications arxiv become cs.ai cs.lg deep learning divergence generalized however machine machine learning management multiple role type