Reasoning about Causal Models with Infinitely Many Variables
Joseph Y. Halpern, Spencer Peters
2022年份
16被引次数
3顶会引用
摘要
Generalized structural equations models (GSEMs) (Peters and Halpern 2021), are, as the name suggests, a generalization of structural equations models (SEMs). They can deal with (among other things) infinitely many variables with infinite ranges, which is critical for capturing dynamical systems. We provide a sound and complete axiomatization of causal reasoning in GSEMs that is an extension of the sound and complete axiomatization provided by Halpern (2000) for SEMs. Considering GSEMs helps clarify what properties Halpern's axioms capture.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper3
- Do Not Marginalize Mechanisms, Rather Consolidate!Moritz Willig, Matej Zecevic, Devendra Singh Dhami, Kristian KerstingNeurIPS 2023 · 被引用 3 次
- Temporal Causal Reasoning with (Non-Recursive) Structural Equation ModelsMaksim Gladyshev, Natasha Alechina, Mehdi Dastani, Dragan Doder 等AAAI 2025 · 被引用 2 次
- A Counterfactual Semantics for Hybrid Dynamical SystemsAndy Zane, Dmitry Batenkov, Rafal Urbaniak, Jeremy Zucker 等NeurIPS 2025
相关 Paper
- Identifiability of Direct Effects from Summary Causal GraphsSimon Ferreira, Charles K. AssaadAAAI 2024 · 被引用 13 次
- Provably Efficient Neural Estimation of Structural Equation Models: An Adversarial ApproachLuofeng Liao, You-Lin Chen, Zhuoran Yang, Bo Dai 等NeurIPS 2020 · 被引用 40 次
- Relational Structural Causal ModelsAdiba Ejaz, Elias BareinboimICML 2026
- Causal Discovery and Inference through Next-Token PredictionEivinas Butkus, Nikolaus KriegeskorteNeurIPS 2025 · 被引用 3 次
- Answering Complex Causal Queries With the Maximum Causal Set EffectZachary MarkovichNeurIPS 2021
