Disentangling Doubt in Deep Causal AI
This work addresses the need for interpretable uncertainty in high-stakes causal AI applications, offering a diagnostic tool for detecting uncertainty sources, though it is incremental as it builds on existing deep twin-network models.
The paper tackled the problem of uncertainty quantification in deep causal-effect models by proposing a factorized Monte Carlo Dropout framework that splits predictive variance into representation and prediction uncertainties, achieving well-calibrated intervals (ECE < 0.03) and showing that representation uncertainty dominates under covariate shifts.
Accurate individual treatment-effect estimation in high-stakes applications demands both reliable point predictions and interpretable uncertainty quantification. We propose a factorized Monte Carlo Dropout framework for deep twin-network models that splits total predictive variance into representation uncertainty (sigma_rep) in the shared encoder and prediction uncertainty (sigma_pred) in the outcome heads. Across three synthetic covariate-shift regimes, our intervals are well-calibrated (ECE < 0.03) and satisfy sigma_rep^2 + sigma_pred^2 ~ sigma_tot^2. Additionally, we observe a crossover: head uncertainty leads on in-distribution data, but representation uncertainty dominates under shift. Finally, on a real-world twins cohort with induced multivariate shifts, only sigma_rep spikes on out-of-distribution samples (delta sigma ~ 0.0002) and becomes the primary error predictor (rho_rep <= 0.89), while sigma_pred remains flat. This module-level decomposition offers a practical diagnostic for detecting and interpreting uncertainty sources in deep causal-effect models.