CorrFlow: Exact and Permutation-Equivariant Flow Matching on the Correlation Elliptope
Correlation matrices combine nonlinear positive-definiteness constraints with a simultaneous row-column permutation symmetry.
ProofPaper ↗
Key points
- We introduce CorrFlow, which separates them.
- A graph flow-matching network learns the empirical distribution in those coordinates and is permutation equivariant: reordering the variables only reorders the output.
- We compare a conditional CorrGAN reimplementation, image diffusion, and CorrFlow on $80\times80$ Taiwan equity matrices using five seeds per neural method.
- CorrFlow produces 100% valid draws without repair and obtains feature sliced-Wasserstein distance $.712\pm.141$, versus $4.339\pm.252$ for CorrGAN and $4.610\pm.191$ for image diffusion after their invalid outputs are projected back to the correlation space.
Sources (1)
- [1]CorrFlow: Exact and Permutation-Equivariant Flow Matching on the Correlation ElliptopearXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 01:53 PM
Correlation matrices combine nonlinear positive-definiteness constraints with a simultaneous row-column permutation symmetry.
We introduce CorrFlow, which separates them.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 9, 2026Qwen/Qwen-Image-2.1-Turbo
- Oct 9, 2026Learning Representations to Guide Pixel Diffusion Transformers
- Oct 9, 2026Rethinking Relative Policy Differences Transfer of On-Policy Distillation
- Oct 9, 2026InstantFusion: A Shared Latent Interface for Heterogeneous Image Generators
- Oct 9, 2026Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark
- Oct 8, 2026Normalizing Trajectory Models