PermFlow applies conditional flow matching on the affine subspace of doubly stochastic matrices with a closed-form tangent projector and nearest-target coupling to capture multimodal permutation distributions.
arXiv preprint arXiv:2006.06663 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Radial Compensation derives a specific tangent-space base distribution that preserves geodesic-radial likelihoods and chart-invariant Fisher information while maintaining isotropy, decoupling statistical modeling from numerical chart choice in manifold generative models.
citing papers explorer
-
Learning Unbiased Permutations via Flow Matching
PermFlow applies conditional flow matching on the affine subspace of doubly stochastic matrices with a closed-form tangent projector and nearest-target coupling to capture multimodal permutation distributions.
-
Radial Compensation: Fixing Radius Distortion in Chart-Based Generative Models on Riemannian Manifolds
Radial Compensation derives a specific tangent-space base distribution that preserves geodesic-radial likelihoods and chart-invariant Fisher information while maintaining isotropy, decoupling statistical modeling from numerical chart choice in manifold generative models.