TY - JOUR

T1 - Toward Learning Distributions of Distributions

AU - Wohlstein, Moritz

AU - Brefeld, Ulf

N1 - Conference code: 6

PY - 2025

Y1 - 2025

N2 - We propose a novel generative deep learning architecture based on generative moment matching networks. The objective of our model is to learn a distribution over distributions and generate new sample distributions following the (possibly complex) distribution of training data. We derive a custom loss function for our model based on the maximum mean discrepancy test. Our model is evaluated on different datasets where we investigate the influence of hyperparameters on performance.

AB - We propose a novel generative deep learning architecture based on generative moment matching networks. The objective of our model is to learn a distribution over distributions and generate new sample distributions following the (possibly complex) distribution of training data. We derive a custom loss function for our model based on the maximum mean discrepancy test. Our model is evaluated on different datasets where we investigate the influence of hyperparameters on performance.

KW - Informatics

UR - http://www.scopus.com/inward/record.url?scp=85219101038&partnerID=8YFLogxK

M3 - Conference article in journal

AN - SCOPUS:85219101038

VL - 265

SP - 269

EP - 275

JO - Proceedings of Machine Learning Research

JF - Proceedings of Machine Learning Research

SN - 2640-3498

T2 - 6th Northern Lights Deep Learning Conference - NLDL 2025

Y2 - 7 January 2025 through 10 January 2025

ER -