analiza aiqbench
ADIGen addresses critical limitations in counterfactual generation by integrating Riesz regression and causal invariance to ensure robustness against distribution shifts and nuisance model misspecification. The framework's theoretical guarantees, including excess-risk bounds and doubly robust properties, offer a significant advancement for decision-making under complex, high-dimensional interventions. This work provides a rigorous foundation for improving generalization in causal inference tasks where existing methods suffer from instability and bias.
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. We introduce ADIGen, a framework for automatic, debiased, and invariant counterfactual generation under general interventions, including high-dimensional interventions and outcomes. ADIGen combines Riesz regression to avoid unstable density-ratio estimation, causal invariance to improve generalization under distribution shift, and orthogonal statistical learning to obtain doubly robust guarantees against nuisance model misspecification. We provide excess-risk bounds showing that ADIGen controls counterfactual risk under general interventions, with a product-bias nuisance remainder and an invariant risk bound across environments.
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. We introduce ADIGen, a framework for automatic, debiased, and invariant counterfactual generation under general interventions, including high-dimensional interventions and outcomes. ADIGen combines Riesz regression to avoid unstable density-ratio estimation, causal invariance to improve generalization under distribution shift, and orthogonal statistical learning to obtain doubly robust guarantees against nuisance model misspecification. We provide excess-risk bounds showing that ADIGen controls counterfactual risk under general interventions, with a product-bias nuisance remainder and an invariant risk bound across environments.
Machine Learning (stat.ML); Machine Learning (cs.LG)
arXiv:2606.07399 [stat.ML]
(or arXiv:2606.07399v1 [stat.ML] for this version)
https://doi.org/10.48550/arXiv.2606.07399 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 204 cuvinte
Subiecte conexe
Automatic, Debiased, and Invariant Counterfactual Generation under General Interventions
arXiv · 25 aug. 2026
The Entangled Dimensions of Decision Theory
LessWrong · 30 iul. 2026
Why do models task game?
AI Alignment Forum · 6 aug. 2026
Links #5: 2026/07
LessWrong · 31 iul. 2026