Andres Aradillas Fernandez, Victor Chernozhukov, Carlos Cinelli, Sven Klaassen, Whitney Newey, Martin Spindler, Jan Teichert-Kluge, Suhas Vijaykumar
arXiv 1 Oct 2026 · Econometrics
arXiv:2610.01935 · PDF · Extracted main text
Text, images, and other rich covariates are increasingly compressed into AI-learned representations and then used as controls in causal analysis. We study when this approach is valid and develop a practical framework for causal inference with learned representations. For a broad class of estimands, an imperfect representation distorts the target causal parameter by the product of two representation errors: one in the outcome regression and one in the balancing weight (or Riesz representer). This yields three constructive results. First, cross-fitted double machine learning (DML) provides valid Wald inference for the representation-dependent target. When representation errors are small, the same interval covers the causal parameter, and it can even attain the semiparametric efficiency bound. Second, fold-wise representation learning (or fine-tuning) is compatible with DML inference for the causal parameter. To this end, we develop convex- and star-aggregation pipelines for learning and combining representations. Third, when representation errors are substantial, we can provide interpretable sensitivity regions and root-$n$ inference for their endpoints. In a multi-modal demand application, seven representation-specific estimates and their star aggregate all imply a negative near-unit elasticity for rank-based price response, and the result remains robust over the reported sensitivity grid.
appendix boundary found by appendix_command · 53% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Chernozhukov, Victor and Newey, Whitney K. and Singh, Rahul (2022) Automatic Debiased Machine Learning of Causal and Structural Effects self | 1.000 | 8 | 3 | 100% |
| 2 | Chernozhukov, Victor and Cinelli, Carlos and Newey, Whitney K. and S… (2026) Long Story Short: Omitted Variable Bias in Causal Machine Learning self | 1.000 | 7 | 3 | 100% |
| 3 | Chernozhukov, Victor and Chetverikov, Denis and Demirer, Mert and Du… (2018) Double/Debiased Machine Learning for Treatment and Structural Parameters self | 0.811 | 4 | 2 | 100% |
| 4 | van der Vaart, Aad W (1998) Asymptotic Statistics | 0.737 | 4 | 3 | 50% |
| 5 | Bickel, Peter J. and Klaassen, Chris A. J. and Ritov, Ya'acov and We… (1993) Efficient and Adaptive Estimation for Semiparametric Models | 0.511 | 2 | 2 | 50% |
| 6 | Chernozhukov, Victor and Newey, Whitney K. and Quintas-Martinez, Vic… (2024) Automatic Debiased Machine Learning via Riesz Regression self | 0.511 | 2 | 1 | 100% |
| 7 | van der Laan, Mark J. and Polley, Eric C. and Hubbard, Alan E (2007) Super Learner | 0.511 | 2 | 1 | 100% |
| 8 | Athey, Susan and Imbens, Guido W (2019) Machine Learning Methods That Economists Should Know About | 0.405 | 1 | 1 | 100% |
| 9 | Audibert, Jean-Yves (2007) Progressive mixture rules are deviation suboptimal | 0.405 | 1 | 1 | 100% |
| 10 | Belloni, Alexandre and Chernozhukov, Victor and Hansen, Christian (2014) High-Dimensional Methods and Inference on Structural and Treatment Effects self | 0.405 | 1 | 1 | 100% |
Showing the top 10 of 25 scored citations.