Pairwise distance-based costs are crucial for self-supervised and contrastive feature learning. Mixture Density Networks (MDNs) are a widely used approach for generative models and density approximation, using neural networks to produce multiple centers that define a Gaussian mixture. By combining MDNs with contrastive costs, this paper proposes data density approximation using four types of kernelized matrix costs in the Hilbert space: the scalar cost, the vector-matrix cost, the matrix-matrix cost (the trace of Schur complement), and the SVD cost (the nuclear norm), for learning multiple centers required to define a mixture density.
@article{arxiv.2509.24076,
title = {A Family of Kernelized Matrix Costs for Multiple-Output Mixture Neural Networks},
author = {Bo Hu and José C. Príncipe},
journal= {arXiv preprint arXiv:2509.24076},
year = {2025}
}