Manifold-Aware Perturbations for Constrained Generative Modeling

Excerpt

arXiv:2601.23151v2 Announce Type: replace Abstract: Generative models have enjoyed widespread success in a variety of applications. However, they encounter inherent mathematical limitations in modeling distributions where samples are constrained by equalities, as is frequently the setting in scientific domains. In this work, we develop a computationally cheap, mathematically justified, and highly flexible distributional modification for combating known pitfalls in equality-constrained generative