We study counterfactual prediction under assignment bias and propose a mathematically grounded, information-theoretic approach that removes treatment-covariate dependence without adversarial training. Starting from a bound that links the counterfactual-factual risk gap to mutual information, we learn a stochastic representation Z that is predictive of outcomes while minimizing I(Z; T). We derive a tractable variational objective that upper-bounds the information term and couples it with a supervised decoder, yielding a stable, provably motivated training criterion. The framework extends naturally to dynamic settings by applying the information penalty to sequential representations at each decision time. We evaluate the method on controlled numerical simulations and a real-world clinical dataset, comparing against recent state-of-the-art balancing, reweighting, and adversarial baselines. Across metrics of likelihood, counterfactual error, and policy evaluation, our approach performs favorably while avoiding the training instabilities and tuning burden of adversarial schemes.

翻译：我们研究了分配偏置下的反事实预测问题，并提出了一种基于数学和信息论的方法，无需对抗训练即可消除处理变量与协变量之间的依赖。通过推导连接反事实-事实风险差距与互信息的理论界限，我们学习了既能预测结果又能最小化互信息I(Z;T)的随机表示Z。我们推导出一个可处理的变分目标函数，该函数对信息项进行上界约束，并与监督解码器耦合，从而形成稳定且具有严格理论动机的训练准则。该框架通过将信息惩罚项应用于每个决策时刻的序列表示，可自然扩展至动态场景。我们在受控数值模拟和真实临床数据集上评估了该方法，并与近期最优的平衡、重加权及对抗基线方法进行了比较。在似然性、反事实误差和政策评估等指标上，我们的方法表现优越，同时避免了对抗性方案中的训练不稳定性和调参负担。