Paper: arXiv 2610.13606

Authors: Gautier Marti

Abstract

Correlation matrices combine nonlinear positive-definiteness constraints with a simultaneous row-column permutation symmetry. Their generation therefore involves two distinct problems. First, every output must remain on the correlation elliptope, irrespective of how its variables are ordered. Second, the generator must learn the domain-specific distribution occupied by empirical data inside that valid space. Existing financial image generators mix these problems: they learn ordered matrix entries and repair invalid draws afterward. We introduce CorrFlow, which separates them. A generalized Fisher transform maps full-rank correlation matrices bijectively to unconstrained coordinates, guaranteeing valid outputs without projection. 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. It also improves this distance over historical lookup, while lookup retains higher local coverage. These results support the combined construction under the evaluated training budget; they do not establish superiority over fully tuned image models or isolate the contribution of each component.

Complexity vs Empirical Score

  • Math Complexity: 8.0/10
  • Empirical Rigor: 8.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: This paper presents a highly novel approach to generating correlation matrices using geometric deep learning and flow matching, addressing critical issues of validity and permutation equivariance. The empirical evaluation is robust, comparing against strong baselines and providing detailed experimental protocols. The mathematical underpinnings are sophisticated yet well-explained.

Research Flowchart

  flowchart TD
    A[Research Goal: Generate Valid & Permutation-Equivariant Correlation Matrices] --> B{Methodology: Separate Validity & Distribution Learning};
    B --> C1[Step 1: Generalized Fisher Transform for Validity];
    B --> C2[Step 2: Permutation-Equivariant Graph Flow-Matching for Distribution];
    C1 & C2 --> D[Data: 80x80 Taiwan Equity Correlation Matrices];
    D --> E[Computational Processes: CorrFlow, CorrGAN (reimplementation), Image Diffusion];
    E --> F[Key Findings: CorrFlow achieves 100% valid draws & lowest Feature Sliced-Wasserstein Distance (0.712 +/- 0.141)];