提出双鲁棒生成框架，有效减少反事实生成中的系统偏差。
DoubleGen: Debiased Generative Modeling of Counterfactuals
- 引入双辅助模型（倾向性与结果模型）改进生成训练目标
- 仅需一个模型正确即可消除混淆偏差，且在有限样本下有理论保证
- 适用于扩散模型、流匹配等，适合因果推断与生成建模交叉研究者
反事实生成模型面临两大偏差：混淆偏差（未考虑干预组与非干预组的系统差异）和误设偏差（依赖辅助模型估计但模型设定错误）。本文提出DoubleGen，一种双重鲁棒的生成建模范式，通过修改生成训练目标，引入倾向性模型与结果模型两个辅助模型，在仅一个模型正确时仍能有效缓解混淆偏差。我们给出了该鲁棒性的有限样本保证，并建立了DoubleGen达到最优收敛率（oracle optimality）及极小极大最优率的条件。通过扩散模型、流匹配与自回归语言模型三个实例验证了方法的有效性。
原文摘要 · Abstract (English)
Generative models for counterfactual outcomes face two key sources of bias. Confounding bias arises when approaches fail to account for systematic differences between those who receive the intervention and those who do not. Misspecification bias arises when methods attempt to address confounding through estimation of an auxiliary model, but specify it incorrectly. We introduce DoubleGen, a doubly robust framework that modifies generative modeling training objectives to mitigate these biases. The new objectives rely on two auxiliaries -- a propensity and outcome model -- and successfully address confounding bias even if only one of them is correct. We provide finite-sample guarantees for this robustness property. We further establish conditions under which DoubleGen achieves oracle optimality -- matching the convergence rates standard approaches would enjoy if interventional data were available -- and minimax rate optimality. We illustrate DoubleGen with three examples: diffusion models, flow matching, and autoregressive language models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。