Metraipolis › archive › dc_e353528eb17d

Does Predictive Performance Translate to Causal Performance? Evaluating tabular foundation models as nuisance learners for causal effect estimation — arXiv:2611.11381

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.11381
License (as archived)
CC0-1.0
Archived
2026-11-10T18:43:21.929Z
SHA-256 of the archived text
98b58effffab84b24fe025f5d36255736a87dd151f1758a519f8119ed5b40d3f
Stable URL of this page
https://metraipolis.com/documento/dc_e353528eb17d

How to cite

Does Predictive Performance Translate to Causal Performance? Evaluating tabular foundation models as nuisance learners for causal effect estimation — arXiv:2611.11381 — arXiv (en), https://arxiv.org/abs/2611.11381 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e353528eb17d (Metraipolis archive dc_e353528eb17d, sha256 98b58effffab84b24fe025f5d36255736a87dd151f1758a519f8119ed5b40d3f)
BibTeX
@misc{dce353528eb17d,
  title = {Does Predictive Performance Translate to Causal Performance? Evaluating tabular foundation models as nuisance learners for causal effect estimation — arXiv:2611.11381},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.11381},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e353528eb17d; sha256 98b58effffab84b24fe025f5d36255736a87dd151f1758a519f8119ed5b40d3f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11381. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tabular foundation models based on prior-data fitted networks (PFNs) achieve strong predictive performance, but their value for causal inference is unclear. We evaluated whether PFNs, which predict through in-context learning, could match or outperform conventional nuisance learners in supporting accurate causal estimation and reliable uncertainty quantification (inference). Learners modeled propensity scores and outcome regressions within doubly robust estimators of average causal effects, with and without cross-fitting, across synthetic and semi-synthetic settings with varying confounding complexity and effect heterogeneity. Under simple parametric data-generating processes, the PFNs were competitive with correctly specified parametric regressions and ensembles containing them. In more complex settings, they outperformed all conventional learners evaluated, including richly specified Super Learner ensembles, for both accuracy and uncertainty quantification. As sample size increased, only the two PFN models (TabPFN and Mitra) consistently approached nominal confidence interval coverage, whereas under-coverage persisted for conventional learners. In some settings, PFNs achieved near-nominal coverage and well-calibrated standard errors even without cross-fitting. At the smallest sample size (n=200) and in the higher-dimensional semi-synthetic settings, PFNs and other flexible learners exhibited poor coverage without cross-fitting. For PFNs, this appeared to be driven by propensity score overfitting consistent with in-sample memorization of treatment labels. These findings highlight the promise of prior-data fitted networks as in-context nuisance learners for causal estimation, while underscoring the need for further evaluation in challenging settings.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Applications (stat.AP) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Methodology (stat.ME); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.11381 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-10T18:37:37.639Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).