arXiv:2605.27473v1 Announce Type: new 
Abstract: Estimating how much an intervention helps a given individual the conditional average treatment effect (CATE) is increasingly central to decision-making in medicine, economics, and policy, where an estimate is most useful when accompanied by a calibrated uncertainty interval. We study the few-placebo regime, in which one treatment arm is much smaller than the other, as arises in unequal-allocation trials and small-holdout $A/B$ tests. The standard estimator in this setting is the X-Learner, and a natural way to obtain credible intervals is to make its second stage Bayesian. We show that these intervals under-cover: they contain the true effect less often than their nominal level. We trace this to a structural cause the X-Learner's regression target inherits the bias of a nuisance model fitted to the small arm, so the posterior is centered away from the true effect and we find that the standard remedy, regressing an orthogonal doubly-robust score, is also unreliable here, since the regime's limited overlap leaves the estimator either highly variable or, once stabilized, biased once more. Both consequences reflect a pattern that extends beyond causal inference: a separately estimated variance is attached to a point estimate of a hard-to-learn quantity, and the point estimate's bias is not captured by that variance. We propose GP-CATE, which models each arm's outcome surface with a Gaussian process, so the scarce arm's uncertainty enters the posterior directly rather than as an unmodelled bias. Across synthetic and semi-synthetic benchmarks, GP-CATE attains calibrated coverage where the estimators we compare against including Causal Forest and BART do not, at the cost of intervals that are appropriately wide when the data are uninformative.

دراسة جديدة نشرت على arXiv تستكشف تقدير تأثير العلاج المتوسط الشرطي (CATE) باستخدام العمليات الغاوسية، وخاصة في نظام القليل من الأدوية الوهمية حيث يكون أحد أذرع العلاج أصغر بكثير. تسلط الأبحاث الضوء على قيود طريقة X-Learner، كاشفة أن نهجها البايزي القياسي يؤدي إلى عدم تغطية موثوقة، مما لا يعكس بدقة التأثيرات الحقيقية للعلاج.

Un nuevo estudio publicado en arXiv explora la estimación del Efecto Promedio de Tratamiento Condicional (CATE) utilizando Procesos Gaussianos, particularmente en el régimen de pocos placebos donde un brazo de tratamiento es significativamente más pequeño. La investigación destaca las limitaciones del método X-Learner, revelando que su enfoque bayesiano estándar resulta en intervalos creíbles que no cubren adecuadamente, lo que no refleja con precisión los verdaderos efectos del tratamiento.

Une nouvelle étude publiée sur arXiv examine l'estimation de l'effet de traitement moyen conditionnel (CATE) à l'aide de processus gaussiens, en particulier dans le régime de peu de placebos où un bras de traitement est significativement plus petit. La recherche met en évidence les limites de la méthode X-Learner, révélant que son approche bayésienne standard entraîne une sous-couverture des intervalles crédibles, qui ne reflètent pas avec précision les véritables effets du traitement.

A new study published on arXiv explores the estimation of the Conditional Average Treatment Effect (CATE) using Gaussian Processes, particularly in the few-placebo regime where one treatment arm is significantly smaller. The research highlights the limitations of the X-Learner method, revealing that its standard Bayesian approach results in under-covering credible intervals, which do not accurately reflect the true treatment effects.