The Unified Non-Convex Framework for Robust Causal Inference: Overcoming the Gaussian Barrier and Optimization Fragility

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Uehara, Eichi
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912726922559488
author Uehara, Eichi
author_facet Uehara, Eichi
contents This document proposes a Unified Robust Framework that re-engineers the estimation of the Average Treatment Effect on the Overlap (ATO). It synthesizes gamma-Divergence for outlier robustness, Graduated Non-Convexity (GNC) for global optimization, and a "Gatekeeper" mechanism to address the impossibility of higher-order orthogonality in Gaussian regimes.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19284
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Unified Non-Convex Framework for Robust Causal Inference: Overcoming the Gaussian Barrier and Optimization Fragility
Uehara, Eichi
Machine Learning
Methodology
62G35, 62J07
G.3; I.2.6
This document proposes a Unified Robust Framework that re-engineers the estimation of the Average Treatment Effect on the Overlap (ATO). It synthesizes gamma-Divergence for outlier robustness, Graduated Non-Convexity (GNC) for global optimization, and a "Gatekeeper" mechanism to address the impossibility of higher-order orthogonality in Gaussian regimes.
title The Unified Non-Convex Framework for Robust Causal Inference: Overcoming the Gaussian Barrier and Optimization Fragility
topic Machine Learning
Methodology
62G35, 62J07
G.3; I.2.6
url https://arxiv.org/abs/2511.19284