Saved in:
Bibliographic Details
Main Authors: Rezvan, Reza, Gille, Gustav, Schauer, Moritz, Torkar, Richard
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.02793
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Flow matching learns a velocity field that transports a base distribution to data. We study how small latent perturbations propagate through these flows and show that Jacobian-vector products (JVPs) provide a practical lens on dependency structure in the generated features. We derive closed-form expressions for the optimal drift and its Jacobian in Gaussian and mixture-of-Gaussian settings, revealing that even globally nonlinear flows admit local affine structure. In low-dimensional synthetic benchmarks, numerical JVPs recover the analytical Jacobians. In image domains, composing the flow with an attribute classifier yields an attribute-level JVP estimator that recovers empirical correlations on MNIST and CelebA. Conditioning on small classifier-Jacobian norms reduces correlations in a way consistent with a hypothesized common-cause structure, while we emphasize that this conditioning is not a formal do intervention.