{"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/robust-learning-of-fixed-structure-bayesian","title":"Robust Learning of Fixed-Structure Bayesian Networks","arxiv_id":"1606.07384","date":"2016-06-23","proceeding":"NeurIPS 2018 12","authors":["Yu Cheng","Ilias Diakonikolas","Daniel Kane","Alistair Stewart"],"abstract":"We investigate the problem of learning Bayesian networks in a robust model\nwhere an $\\epsilon$-fraction of the samples are adversarially corrupted. In\nthis work, we study the fully observable discrete case where the structure of\nthe network is given. Even in this basic setting, previous learning algorithms\neither run in exponential time or lose dimension-dependent factors in their\nerror guarantees. We provide the first computationally efficient robust\nlearning algorithm for this problem with dimension-independent error\nguarantees. Our algorithm has near-optimal sample complexity, runs in\npolynomial time, and achieves error that scales nearly-linearly with the\nfraction of adversarially corrupted samples. Finally, we show on both synthetic\nand semi-synthetic data that our algorithm performs well in practice.","url_abs":"http://arxiv.org/abs/1606.07384v2","url_pdf":"http://arxiv.org/pdf/1606.07384v2.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":"robust-learning-of-fixed-structure-bayesian","repo_url":"https://github.com/chycharlie/robust-bn-faster","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1606.07384","atlas_url":"https://app.syntology.ai/?focus=1606.07384","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}