对称性与因果性：超越独立同分布（IID）数据的因果效应识别

中文摘要 AI 辅助

在自然科学中，对称性与因果关系无处不在，但在复杂机器学习任务（如强化学习中的世界建模）中，它们似乎难以被利用。本文提出一种基于数据中使因果机制保持不变的对称性的统计系统形式化描述，形成了一种抽象、简洁且通用的因果推理数学语言。本文对该语言的模型与查询进行形式化描述，搭建了其形式化基础，并提供了在该形式体系内从数据中对其进行数学严格识别的形式化基础设施与策略。该方法可复现与匹配独立同分布（IID）数据的标准理论结果，以及实验数据与非实验数据的迁移结果。但其主要目的是统一并大幅扩展因果推理的范围，超越IID数据，处理无法通过do-干预或软干预捕捉的复杂因果查询。这种对数据建模中因果相关方面的新视角，还为c-组件、对冲（hedges）等知名结构提供了新的阐释，同时包含缺失数据方面的内容，且天生适用于迁移与鲁棒性属性的描述。

英文摘要

In the natural sciences, symmetries and cause-effect relationships are ubiquitous. Yet for complex machine-learning tasks, like world-modeling in reinforcement learning, they appear difficult to harness. We propose a formal description of statistical systems based on symmetries in data leaving causal mechanisms invariant. The result is an abstract, simple and general mathematical language for causal reasoning. This paper provides formal descriptions of models and queries, setting up this language, and the formal infrastructure and strategies for their mathematically rigorous identification from data within this formalism. This approach reproduces and matches standard theoretical results on IID data and transport of experimental and non-experimental data. But its main purpose is to unify and substantially extend the scope of causal reasoning, in going beyond IID data and in approaching complex causal queries not captured by do- or soft-interventions. This new perspective on causally relevant aspects of data-modeling additionally sheds new light on well-known structures like c-components or hedges but also includes aspects of missing data and is inherently well-suited for the description of transfer and robustness properties.

发表机构

• University of Potsdam（波茨坦大学）

机构由 AI 辅助整理，请以论文原文为准。