Generalization bounds and algorithms for estimating conditional average treatment effect of dosage
We investigate the task of estimating the conditional average causal effect of treatment-dosage pairs from a combination of observational data and assumptions on the causal relationships in the underlying system. This has been a longstanding challenge for fields of study such as epidemiology or economics that require a treatment-dosage pair to make decisions but may not be able to run randomized trials to precisely quantify their effect and heterogeneity across individuals. In this paper, we extend (Shalit et al, 2017) to give new bounds on the counterfactual generalization error in the context of a continuous dosage parameter which relies on a different approach to defining counterfactuals and assignment bias adjustment. This result then guides the definition of new learning objectives that can be used to train representation learning algorithms for which we show empirically new state-of-the-art performance results across several benchmark datasets for this problem, including in comparison to doubly-robust estimation methods.
Code (0)
등록된 구현이 없습니다.
Tasks
counterfactualEpidemiologyGeneralization BoundsRepresentation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Generalization Bounds via Information Density and Conditional Information Density
We present a general approach, based on exponential inequalities, to derive bounds on the generalization error of randomized learning algorithms. Using this approach, we provide bounds on the average generalization error…
Generalization BoundsWhich Algorithms Have Tight Generalization Bounds?
We study which machine learning algorithms have tight generalization bounds. First, we present conditions that preclude the existence of tight generalization bounds. Specifically, we show that algorithms that have certai…
Generalization BoundsOn Leave-One-Out Conditional Mutual Information For Generalization
We derive information theoretic generalization bounds for supervised learning algorithms based on a new measure of leave-one-out conditional mutual information (loo-CMI). Contrary to other CMI bounds, which are black-box…
Generalization Boundsimage-classificationImage ClassificationQuantifying Aleatoric Uncertainty of the Treatment Effect: A Novel Orthogonal Learner
Estimating causal quantities from observational data is crucial for understanding the safety and effectiveness of medical treatments. However, to make reliable inferences, medical practitioners require not only estimatin…
B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confounding
Estimating heterogeneous treatment effects from observational data is a crucial task across many fields, helping policy and decision-makers take better actions. There has been recent progress on robust and efficient meth…
valid