Frequentist Consistency of Prior-Data Fitted Networks for Causal Inference

TL;DR

This paper investigates the frequentist consistency of prior-data fitted networks (PFNs) in causal inference, identifies bias issues, and proposes a calibration method with martingale posteriors to improve uncertainty quantification.

Contribution

It introduces a calibration procedure using one-step posterior correction (OSPC) to restore frequentist consistency of PFN-based estimators in causal inference.

Findings

OSPC helps restore frequentist consistency of PFN estimators.

Calibrated PFNs produce asymptotically correct uncertainty estimates.

Experiments show improved finite-sample calibration compared to other methods.

Abstract

Foundation models based on prior-data fitted networks (PFNs) have shown strong empirical performance in causal inference by framing the task as an in-context learning problem.However, it is unclear whether PFN-based causal estimators provide uncertainty quantification that is consistent with classical frequentist estimators. In this work, we address this gap by analyzing the frequentist consistency of PFN-based estimators for the average treatment effect (ATE). (1) We show that existing PFNs, when interpreted as Bayesian ATE estimators, can exhibit prior-induced confounding bias: the prior is not asymptotically overwritten by data, which, in turn, prevents frequentist consistency. (2) As a remedy, we suggest employing a calibration procedure based on a one-step posterior correction (OSPC). We show that the OSPC helps to restore frequentist consistency and can yield a semi-parametric Bernstein-von Mises theorem for calibrated PFNs (i.e., both the calibrated PFN-based estimators and the classical semi-parametric efficient estimators converge in distribution with growing data size). (3) Finally, we implement OSPC through tailoring martingale posteriors on top of the PFNs. In this way, we are able to recover functional nuisance posteriors from PFNs, required by the OSPC. In multiple (semi-)synthetic experiments, PFNs calibrated with our martingale posterior OSPC produce ATE uncertainty that (i) asymptotically matches frequentist uncertainty and (ii) is well calibrated in finite samples in comparison to other Bayesian ATE estimators.