通过压缩数据，让因果关系在多环境中学出来。
Algorithmic causal structure emerging through compression
- 用压缩最小化柯尔莫哥洛夫复杂度来推导因果结构
- 无需干预目标信息即可发现对称与因果模式
- 适合研究大模型中隐含因果机制的学者
我们探讨了因果性、对称性与压缩之间的关系。在传统因果可识别性不成立的情况下，拓展并推广了学习与压缩之间的已知联系。提出一个框架，使因果性作为跨多个环境压缩数据的结果而浮现。定义算法因果性为传统因果可识别性假设不成立时的替代因果定义。我们证明，仅通过最小化柯尔莫哥洛夫复杂度的上界，即可在无干预目标知识的前提下，涌现出算法因果与对称结构。我们推测这些见解可能为大型语言模型等机器学习模型中因果关系的隐含涌现提供新视角。
原文摘要 · Abstract (English)
We explore the relationship between causality, symmetry, and compression. We build on and generalize the known connection between learning and compression to a setting where causal models are not identifiable. We propose a framework where causality emerges as a consequence of compressing data across multiple environments. We define algorithmic causality as an alternative definition of causality when traditional assumptions for causal identifiability do not hold. We demonstrate how algorithmic causal and symmetric structures can emerge from minimizing upper bounds on Kolmogorov complexity, without knowledge of intervention targets. We hypothesize that these insights may also provide a novel perspective on the emergence of causality in machine learning models, such as large language models, where causal relationships may not be explicitly identifiable.
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。