

















Abstract:We introduce boundary quotients and present a framework for learning densities on manifolds that arise as boundary quotients of simpler domains. We show that this framework can be used to construct normalizing flows on quotient manifolds $N/G$, where a discrete group $G$ acts on $N$. We instantiate this construction for genus-$g$ surfaces $\Sigma_g$. When $G$ is finite, we show applicability to symmetry aware learning; we demonstrate this on cyclic quotients of the 3-sphere. Experiments on lens spaces show that simple pre-quotient RealNVP models can achieve strong results while being substantially cheaper to evaluate.
| Subjects: | Machine Learning (cs.LG); Probability (math.PR) |
| Cite as: | arXiv:2511.22882 [cs.LG] |
| (or arXiv:2511.22882v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2511.22882 arXiv-issued DOI via DataCite |
From: William Ghanem [view email]
[v1]
Fri, 28 Nov 2025 05:12:27 UTC (1,100 KB)
[v2]
Thu, 7 May 2026 14:00:56 UTC (1 KB) (withdrawn)
[v3]
Tue, 19 May 2026 18:06:07 UTC (6,533 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。