#machine learning
Jan 2026
Generative Modeling of Discrete Data Using Geometric Latent Subspaces
This work introduces latent subspaces in the exponential parameter space of product manifolds of categorical distributions as a novel approach to learning low-dimensional representations of high-dimensional discrete data.
Daniel Gonzalez-Alvarado, Jonas Cassel, Stefania Petra et al.
· arXiv.org · 0 citations