.png){kind=icon}
返回
Causality-Oriented Robustness: Exploiting General Noise Interventions
.png){kind=icon}
PRE
AI
DOI：10.1080/01621459.2025.2544365.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Since distribution shifts are common in real-world applications, there is a pressing need to develop prediction models that are robust against such shifts. Existing frameworks, such as empirical risk minimization or distributionally robust optimization, either lack generalizability for unseen distributions or rely on postulated distance measures. Alternatively, causality offers a data-driven and structural perspective to robust predictions. However, the assumptions necessary for causal inference can be overly stringent, and the robustness offered by such causal models often lacks flexibility. In this article, we focus on causality-oriented robustness and propose Distributional Robustness via Invariant Gradients (DRIG), a method that exploits general noise interventions in training data for robust predictions against unseen interventions, and naturally interpolates between in-distribution prediction and causality. In a linear setting, we prove that DRIG yields predictions that are robust among a data-dependent class of distribution shifts. Furthermore, we show that our framework includes anchor regression as a special case, and that it yields prediction models that protect against more diverse perturbations. We establish finite-sample results and extend our approach to semi-supervised domain adaptation to further improve prediction performance. Finally, we empirically validate our methods on synthetic simulations and on single-cell and intensive health care datasets. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work.
Keyword:
Distribution shifts
Interventional data
Invariance
Robust prediction
Structural causal models
期刊
J
IF:
3
论文数:
5.2K
被引数:
4.8W
机构
引用论文
Causal inference by using invariant prediction: identification and confidence intervals使用不变预测进行因果推断: 识别和置信区间
OAAI
OAAI分享收藏CAUSAL DANTZIG: FAST INFERENCE IN LINEAR STRUCTURAL EQUATION MODELS WITH HIDDEN VARIABLES UNDER ADDITIVE INTERVENTIONS.png)
ANNALS OF STATISTICSOAAI
ANNALS OF STATISTICSIF3.7
OAAI分享收藏LEARNING MODELS WITH UNIFORM PERFORMANCE VIA DISTRIBUTIONALLY ROBUST OPTIMIZATION通过分布式鲁棒优化学习具有统一性能的模型ANNALS OF STATISTICS
OAAI
ANNALS OF STATISTICSIF3.7
OAAI分享收藏
查看更多内容