Beyond Unimodal Bases: Pullback Geometry for Multimodal Data

Excerpt

arXiv:2610.00708v1 Announce Type: new Abstract: Data-driven Riemannian geometry provides nonlinear interpolation and geometric representations of high-dimensional data. For these operations to be statistically meaningful, paths between observations should preferentially traverse high-likelihood regions. Existing scalable pullback constructions typically use a unimodal Gaussian latent distribution, assuming that the data reside close to a single manifold. For multimodal data, mapping separated mo