Topological Conditional Separation
Michel de Lara, Jean-Philippe Chancelier (CERMICS), Benjamin Heymann
TL;DR
This paper introduces topological conditional separation, extending Pearl's d-separation to broader graph structures, and proves their equivalence beyond acyclic graphs, including infinite cases.
Contribution
It defines topological conditional separation and demonstrates its equivalence to d-separation in more general graph settings.
Findings
Topological conditional separation is equivalent to d-separation.
Extension of d-separation to infinite and cyclic graphs.
Provides a unified framework for conditional independence in complex graphs.
Abstract
Pearl's d-separation is a foundational notion to study conditional independence between random variables. We define the topological conditional separation and we show that it is equivalent to the d-separation, extended beyond acyclic graphs, be they finite or infinite.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning and Algorithms · Computational Drug Discovery Methods · Advanced Control Systems Optimization