{"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/heron-inference-for-bayesian-graphical-models","title":"Heron Inference for Bayesian Graphical Models","arxiv_id":"1802.06526","date":"2018-02-19","proceeding":null,"authors":["Daniel Rugeles","Zhen Hai","Gao Cong","Manoranjan Dash"],"abstract":"Bayesian graphical models have been shown to be a powerful tool for\ndiscovering uncertainty and causal structure from real-world data in many\napplication fields. Current inference methods primarily follow different kinds\nof trade-offs between computational complexity and predictive accuracy. At one\nend of the spectrum, variational inference approaches perform well in\ncomputational efficiency, while at the other end, Gibbs sampling approaches are\nknown to be relatively accurate for prediction in practice. In this paper, we\nextend an existing Gibbs sampling method, and propose a new deterministic Heron\ninference (Heron) for a family of Bayesian graphical models. In addition to the\nsupport for nontrivial distributability, one more benefit of Heron is that it\nis able to not only allow us to easily assess the convergence status but also\nlargely improve the running efficiency. We evaluate Heron against the standard\ncollapsed Gibbs sampler and state-of-the-art state augmentation method in\ninference for well-known graphical models. Experimental results using publicly\navailable real-life data have demonstrated that Heron significantly outperforms\nthe baseline methods for inferring Bayesian graphical models.","url_abs":"http://arxiv.org/abs/1802.06526v1","url_pdf":"http://arxiv.org/pdf/1802.06526v1.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":"heron-inference-for-bayesian-graphical-models","repo_url":"https://github.com/danrugeles/Heron","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}