{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/constraint-based-causal-discovery-for-non","title":"Constraint-based Causal Discovery for Non-Linear Structural Causal Models with Cycles and Latent Confounders","arxiv_id":"1807.03024","date":"2018-07-09","proceeding":null,"authors":["Patrick Forré","Joris M. Mooij"],"abstract":"We address the problem of causal discovery from data, making use of the\nrecently proposed causal modeling framework of modular structural causal models\n(mSCM) to handle cycles, latent confounders and non-linearities. We introduce\n{\\sigma}-connection graphs ({\\sigma}-CG), a new class of mixed graphs\n(containing undirected, bidirected and directed edges) with additional\nstructure, and extend the concept of {\\sigma}-separation, the appropriate\ngeneralization of the well-known notion of d-separation in this setting, to\napply to {\\sigma}-CGs. We prove the closedness of {\\sigma}-separation under\nmarginalisation and conditioning and exploit this to implement a test of\n{\\sigma}-separation on a {\\sigma}-CG. This then leads us to the first causal\ndiscovery algorithm that can handle non-linear functional relations, latent\nconfounders, cyclic causal relationships, and data from different (stochastic)\nperfect interventions. As a proof of concept, we show on synthetic data how\nwell the algorithm recovers features of the causal graph of modular structural\ncausal models.","url_abs":"http://arxiv.org/abs/1807.03024v1","url_pdf":"http://arxiv.org/pdf/1807.03024v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"constraint-based-causal-discovery-for-non","repo_url":"https://github.com/caus-am/sigmasep","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"causal-discovery","task_name":"Causal Discovery"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1807.03024","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}