Get Started
Research questionHow can we estimate counterfactual outcomes with valid uncertainty as treatment patterns shift?Observed data reflect one treatment pattern, while deployment may follow another, so outcomes under hypothetical interventions are not directly observed. Decision-makers need estimates of these counterfactual outcomes together with uncertainty that remains valid across intervention levels.
Machine Learning
Statistical Machine Learning
Latest papersRecent research connected to this question, newest first.Semiparametric Inference for Counterfactual Regression under Intervention-Driven ShiftThe source studies semiparametric counterfactual regression for constrained projections of counterfactual risk. Its theory covers smooth programs with fixed constraints and finite-dimensional programs with estimated linear constraints, using cross-fitted influence-function representations to derive pointwise and uniform inference; simulations and an SMS-reminder application provide finite-sample evidence.research paper · Sep 3, 2026
Related questions
How can extreme quantile treatment effects be estimated under heavy tails while respecting location invariance?How can probabilistic regression provide valid uncertainty estimates for unbounded outcomes?How can regression models produce tight, valid prediction intervals across confidence levels without retraining?How can counterfactual KPI prediction retain finite-sample coverage under hidden confounding with scarce randomized telemetry?
Home
Topics
Search
Library