Unified targeted regularization framework for causal effect estimation with EDF outcomes using neural networks that jointly estimate outcome model, propensity scores, and fluctuation parameter.
Learning Weighted Representations for Generalization Across Designs
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Predictive models that generalize well under distributional shift are often desirable and sometimes crucial to building robust and reliable machine learning applications. We focus on distributional shift that arises in causal inference from observational data and in unsupervised domain adaptation. We pose both of these problems as prediction under a shift in design. Popular methods for overcoming distributional shift make unrealistic assumptions such as having a well-specified model or knowing the policy that gave rise to the observed data. Other methods are hindered by their need for a pre-specified metric for comparing observations, or by poor asymptotic properties. We devise a bound on the generalization error under design shift, incorporating both representation learning and sample re-weighting. Based on the bound, we propose an algorithmic framework that does not require any of the above assumptions and which is asymptotically consistent. We empirically study the new framework using two synthetic datasets, and demonstrate its effectiveness compared to previous methods.
fields
cs.LG 3verdicts
UNVERDICTED 3representative citing papers
Introduces OR-learners that can strictly improve estimation error of standard Neyman-orthogonal learners under the low-dimensional manifold hypothesis, while showing that balancing constraints require additional inductive bias.
Frames causal inference methods as representation learners to derive general and estimable error bounds, extending them to unobserved confounding via robust statistics.
citing papers explorer
-
Targeted Regularization for Causal Effect Estimation with Exponential Dispersion Family Outcomes
Unified targeted regularization framework for causal effect estimation with EDF outcomes using neural networks that jointly estimate outcome model, propensity scores, and fluctuation parameter.
-
Orthogonal Representation Learning for Estimating Causal Quantities
Introduces OR-learners that can strictly improve estimation error of standard Neyman-orthogonal learners under the low-dimensional manifold hypothesis, while showing that balancing constraints require additional inductive bias.
-
Quantifying Error in the Presence of Confounders for Causal Inference
Frames causal inference methods as representation learners to derive general and estimable error bounds, extending them to unobserved confounding via robust statistics.