collaborators

6 papers

cs.LG2026

Optimization-Free Topological Sort for Causal Discovery via the Schur Complement of Score Jacobians

Rui Wu, Hong Xie

Continuous causal discovery typically couples representation learning with structural optimization via non-convex acyclicity penalties, which subjects solvers to local optima and r…

cs.LG2026

The Causal Uncertainty Principle: Manifold Tearing and the Topological Limits of Counterfactual Interventions

Rui Wu, Hong Xie, Yongjun Li

Judea Pearl's do-calculus provides a foundation for causal inference, but its translation to continuous generative models remains fraught with geometric challenges. We establish th…

cs.LG2026

Cohomological Obstructions to Global Counterfactuals: A Sheaf-Theoretic Foundation for Generative Causal Models

Rui Wu, Hong Xie, Yongjun Li

Current continuous generative models (e.g., Diffusion Models, Flow Matching) implicitly assume that locally consistent causal mechanisms naturally yield globally coherent counterfa…

cs.LG2026

Causal Schrödinger Bridges: Constrained Optimal Transport on Structural Manifolds

Rui Wu, Li YongJun

Generative modeling typically seeks the path of least action via deterministic flows (ODE). While effective for in-distribution tasks, we argue that these deterministic paths becom…

cs.LG2026

Smooth, Sparse, and Stable: Finite-Time Exact Skeleton Recovery via Smoothed Proximal Gradients

Rui Wu, Yongjun Li

Continuous optimization has significantly advanced causal discovery, yet existing methods (e.g., NOTEARS) generally guarantee only asymptotic convergence to a stationary point. Thi…

cs.LG2025

The Causal Round Trip: Generating Authentic Counterfactuals by Eliminating Information Loss

Rui Wu, Lizheng Wang, Yongjun Li

Judea Pearl's vision of Structural Causal Models (SCMs) as engines for counterfactual reasoning hinges on faithful abduction: the precise inference of latent exogenous noise. For d…