← Back to all news
arXiv AI By Alexis Bellot, Anish Dhir

Foundation Models for Partial Causal Identification

Read the original on arXiv AI →

The paper introduces causal foundation models that can bound the effects of interventions and counterfactuals using only observational data. It defines a canonical prior with full support over structural causal models with discrete observables, enabling the translation of counterfactual bounding into learning distributions over functions that map data and structural assumptions to causal queries. This approach extends causal foundational modelling to partially-identifiable causal effects, where unobserved confounding leads to multiple compatible values for the effect.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Statistics ML
Sep 28

Identifying Causal Effects Using a Single Proxy Variable

The paper tackles the problem of estimating causal effects when an unobserved confounder is present. It assumes a single, possibly multi‑dimensional proxy variable for the confounder and knowledge of the mechanism that generates this proxy. Under the Single Proxy Identifiability of Causal Effects (SPICE) assumption, the authors prove that the error mechanism is complete and causal effects are identifiable, extending prior proxy‑based results to continuous, multi‑dimensional settings and more flexible functional forms. They also introduce SPICE‑Net, a neural‑network‑based framework for estimating causal effects applicable to both discrete and continuous treatments.

By Silvan Vollmer, Niklas Pfister, Sebastian Weichwald
More like this →
arXiv Machine Learning
Sep 22

Causal Inference with Unobserved Confounding: A Mixture Learning Perspective

The paper introduces a mixture‑learning framework for causal inference with unobserved confounding, treating latent confounders as sources of heterogeneity that create mixture structures in observed data. By assuming suitable structural and identifiability conditions, it shows that recovering the mixing distribution and component mechanisms allows estimation of interventional distributions and causal estimands. The authors illustrate the approach with Bernoulli mixture examples, extend it to high‑dimensional exponential‑family mixtures with dependent outcomes, and relate it to panel‑data settings, latent factor models, and synthetic interventions.

By Mansi Sood, Devavrat Shah
More like this →
arXiv AI
Aug 26

Partial Identification under Causal Orders by Linear Programming

The paper presents a method for partially identifying counterfactual queries without requiring a fully specified causal graph. By exploiting the topological ordering implied by the query itself, the authors transform the identification problem into a linear programming task, enabling bounds on arbitrary counterfactual and nested counterfactual queries. They demonstrate the tightness of these bounds and illustrate the approach on several case studies, showing its usefulness even when causal knowledge is incomplete.

By Eric Rossetto, Alessandro Antonucci
More like this →