Collaborative representations for targeted causal inference under outcome selection
Abstract
Estimating causal effects with missing outcomes requires learning outcome, exposure, and selection models. Flexible propensity learners can predict treatment or missingness well while worsening target estimation by emphasizing instruments, weak-overlap regions, or variation unrelated to outcome-regression bias. We propose a collaborative representation-based targeted learning method for recovered average treatment effects under outcome selection. The method learns low-dimensional exposure and selection representations from cross-fitted pseudo-outcomes that encode outcome-regression drift. A finite candidate library alternates targeted outcome updates with representation updates, and inner cross-validation selects representation complexity, collaboration strength, and regularization using a target-aware risk. We give high-level sufficient conditions for collaborative robustness, consistency, and asymptotic linearity after outer validation-fold targeting. Simulations show finite-sample bias reduction, with explicit bias-variance trade-offs across configurations and relative to competing estimators
Versions
Related
- Majority Dynamics on Resampled Sparse Erdős--Rényi Graphs: Gaussian Winner Selection in Collaborative Agent Networks
- Inference for sparsely sampled Gauss-Markov processes under outcome-dependent dropout
- Studentized inference in randomized experiments when a few units dominate the outcome variation
- Targeted Retrieval, Compact Representations: How CoT Reasoning Improves Long-Context Counting
- Semiparametric inference for a Target Outcome Leveraging Heterogeneous External Summaries of Auxiliary Outcomes
BibTeX
@misc{aguas2026collaborative,
title = {{Collaborative representations for targeted causal inference under outcome selection}},
author = {Johan de Aguas},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.08073},
eprint = {2610.08073},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.08073},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Collaborative representations for targeted causal inference under outcome selection
AU - Johan de Aguas
PY - 2026
DA - 2026/10/06
PB - arXiv
DO - 10.48550/arxiv.2610.08073
UR - https://arxiv.org/abs/2610.08073
AB - Estimating causal effects with missing outcomes requires learning outcome, exposure, and selection models. Flexible propensity learners can predict treatment or missingness well while worsening target estimation by emphasizing instruments, weak-overlap regions, or variation unrelated to outcome-regression bias. We propose a collaborative representation-based targeted learning method for recovered average treatment effects under outcome selection. The method learns low-dimensional exposure and selection representations from cross-fitted pseudo-outcomes that encode outcome-regression drift. A finite candidate library alternates targeted outcome updates with representation updates, and inner cross-validation selects representation complexity, collaboration strength, and regularization using a target-aware risk. We give high-level sufficient conditions for collaborative robustness, consistency, and asymptotic linearity after outer validation-fold targeting. Simulations show finite-sample bias reduction, with explicit bias-variance trade-offs across configurations and relative to competing estimators
ER -