arXiv Machine Learning

Geometry Adaptive Counterfactual Distribution Learning with Diffusion-Guided Smoothing

arXiv:2605. 25811v2 Announce Type: replace-cross Abstract: We study counterfactual distribution learning for high-dimensional outcomes whose laws may concentrate near lower-dimensional structure.

arXiv Machine Learning
Jun 9

Mitigating the Contractivity Trap in Diffusion ODEs via Stein Stabilization

arXiv:2606. 07835v1 Announce Type: new Abstract: A fundamental tension exists in the large-step inference of diffusion models via their deterministic probability flow ordinary differential equation (PF-ODE) trajectories, which we identify as the contractivity trap: efficient inference favors large step sizes, while aggressive steps and highly expressive denoisers can undermine contraction-based stability certificates for error suppression.

By Shigui Li, Delu Zeng
arXiv Machine Learning
Jun 8

Automatic, Debiased, and Invariant Counterfactual Generation under General Interventions

arXiv:2606. 07399v1 Announce Type: cross Abstract: Generative models for counterfactual outcomes have great potential to support decision-making under complex interventions, but existing approaches are limited by unstable estimation, poor generalization across environments, and bias from nuisance model misspecification.

By Raphael C Kim, Jingsen Zhu, Ramin Zabih, Michele Santacatterina