A locally robust, cross-fitted omnibus test detects systematic treatment-effect heterogeneity with respect to low-dimensional covariates while allowing high-dimensional ML-based nuisance estimation across unconfoundedness, DiD, and IV designs.
Applied causal inference powered by ML and AI
5 Pith papers cite this work, alongside 36 external citations. Polarity classification is still indexing.
5
Pith papers citing it
36
external citations · Pith
abstract
An introduction to the emerging fusion of machine learning and causal inference. The book presents ideas from classical structural equation models (SEMs) and their modern AI equivalent, directed acyclical graphs (DAGs) and structural causal models (SCMs), and covers Double/Debiased Machine Learning methods to do inference in such models using modern predictive tools.
years
2026 5representative citing papers
A meta-learning method identifies the conditional mean of task-specific causal demand parameters by conditioning on all prices while masking two demand outcomes, assuming at least two locally exogenous prices per task.
Introduces a transportability-based approach to model population-level exposure effects as a function of effect modifier prevalences for heterogeneity analysis.
Balancing in debiased machine learning for causal effects should be guided by the Neyman orthogonal score, with covariate balancing as a special case appropriate only when regression errors depend solely on covariates.
A tutorial reviewing why traditional prediction models often fail to improve decision quality in stochastic optimization and summarizing key properties and tools of decision-focused learning.
citing papers explorer
-
A Machine-Learning-Compatible Omnibus Test for Treatment Effect Heterogeneity
A locally robust, cross-fitted omnibus test detects systematic treatment-effect heterogeneity with respect to low-dimensional covariates while allowing high-dimensional ML-based nuisance estimation across unconfoundedness, DiD, and IV designs.
-
Causal Multi-Task Demand Learning
A meta-learning method identifies the conditional mean of task-specific causal demand parameters by conditioning on all prices while masking two demand outcomes, assuming at least two locally exogenous prices per task.
-
From Subgroups to Population Composition: A Transportability Approach to Effect Heterogeneity
Introduces a transportability-based approach to model population-level exposure effects as a function of effect modifier prevalences for heterogeneity analysis.
-
Covariate Balancing and Riesz Regression Should Be Guided by the Neyman Orthogonal Score in Debiased Machine Learning
Balancing in debiased machine learning for causal effects should be guided by the Neyman orthogonal score, with covariate balancing as a special case appropriate only when regression errors depend solely on covariates.
-
Decision-Focused Learning: When and Why Traditional Prediction Models Fail
A tutorial reviewing why traditional prediction models often fail to improve decision quality in stochastic optimization and summarizing key properties and tools of decision-focused learning.