paper-with-me

홈 › Papers

Causality--Δ: Jacobian-Based Dependency Analysis in Flow Matching Models

2026-02-02 · Reza Rezvan, Gustav Gille, Moritz Schauer, Richard Torkar arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.02793

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Jacobian Granger Causal Neural Networks for Analysis of Stationary and Nonstationary Data

2022-05-19 · Suryadi, Yew-Soon Ong, Lock Yue Chew

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 Analysis

Interventional Flow Matching: Prospective Dose-Response Forecasting with Velocity-Field Jacobian Regularization

2026-06-28 · Amirreza Dolatpour Fathkouhi, Justin Lee, Heman Shakeri arxiv

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

2024-05-14 · Wanqi Zhou, Shuanghao Bai, Shujian Yu, Qibin Zhao 외

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

2018-03-01 · ICML 2018 7 · Suraj Srinivas, Francois Fleuret

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 Learning

Training Energy-Based Normalizing Flow with Score-Matching Objectives

2023-05-24 · NeurIPS 2023 11 · Chen-Hao Chao, Wei-Fang Sun, Yen-Chang Hsu, Zsolt Kira 외

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…