English

Scaling Riemannian Diffusion Models

Machine Learning 2023-11-01 v1 Differential Geometry Machine Learning

Abstract

Riemannian diffusion models draw inspiration from standard Euclidean space diffusion models to learn distributions on general manifolds. Unfortunately, the additional geometric complexity renders the diffusion transition term inexpressible in closed form, so prior methods resort to imprecise approximations of the score matching training objective that degrade performance and preclude applications in high dimensions. In this work, we reexamine these approximations and propose several practical improvements. Our key observation is that most relevant manifolds are symmetric spaces, which are much more amenable to computation. By leveraging and combining various ans\"{a}tze, we can quickly compute relevant quantities to high precision. On low dimensional datasets, our correction produces a noticeable improvement, allowing diffusion to compete with other methods. Additionally, we show that our method enables us to scale to high dimensional tasks on nontrivial manifolds. In particular, we model QCD densities on SU(n)SU(n) lattices and contrastively learned embeddings on high dimensional hyperspheres.

Keywords

Cite

@article{arxiv.2310.20030,
  title  = {Scaling Riemannian Diffusion Models},
  author = {Aaron Lou and Minkai Xu and Stefano Ermon},
  journal= {arXiv preprint arXiv:2310.20030},
  year   = {2023}
}

Comments

NeurIPS 2023

R2 v1 2026-06-28T13:06:43.376Z