Causality--Δ: Jacobian-Based Dependency Analysis in Flow Matching Models
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Jacobian Granger Causal Neural Networks for Analysis of Stationary and Nonstationary Data
Granger causality is a commonly used method for uncovering information flow and dependencies in a time series. Here we introduce JGC (Jacobian Granger Causality), a neural network-based approach to Granger causality usin…
Time SeriesTime Series AnalysisInterventional Flow Matching: Prospective Dose-Response Forecasting with Velocity-Field Jacobian Regularization
Predicting a patient's physiological trajectory under a planned treatment sequence is a prospective interventional problem, not standard time-series extrapolation. We study this problem in glucose management, where insul…
Jacobian Regularizer-based Neural Granger Causality
With the advancement of neural networks, diverse methods for neural Granger causality have emerged, which demonstrate proficiency in handling complex data, and nonlinear relationships. However, the existing framework of …
Knowledge Transfer with Jacobian Matching
Classical distillation methods transfer representations from a "teacher" neural network to a "student" network by matching their output activations. Recent methods also match the Jacobians, or the gradient of output acti…
Transfer LearningTraining Energy-Based Normalizing Flow with Score-Matching Objectives
In this paper, we establish a connection between the parameterization of flow-based and energy-based generative models, and present a new flow-based modeling approach called energy-based normalizing flow (EBFlow). We dem…