{"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/a-factor-graph-approach-to-automated-design","title":"A Factor Graph Approach to Automated Design of Bayesian Signal Processing Algorithms","arxiv_id":"1811.03407","date":"2018-11-08","proceeding":null,"authors":["Marco Cox","Thijs van de Laar","Bert de Vries"],"abstract":"The benefits of automating design cycles for Bayesian inference-based\nalgorithms are becoming increasingly recognized by the machine learning\ncommunity. As a result, interest in probabilistic programming frameworks has\nmuch increased over the past few years. This paper explores a specific\nprobabilistic programming paradigm, namely message passing in Forney-style\nfactor graphs (FFGs), in the context of automated design of efficient Bayesian\nsignal processing algorithms. To this end, we developed \"ForneyLab\"\n(https://github.com/biaslab/ForneyLab.jl) as a Julia toolbox for message\npassing-based inference in FFGs. We show by example how ForneyLab enables\nautomatic derivation of Bayesian signal processing algorithms, including\nalgorithms for parameter estimation and model comparison. Crucially, due to the\nmodular makeup of the FFG framework, both the model specification and inference\nmethods are readily extensible in ForneyLab. In order to test this framework,\nwe compared variational message passing as implemented by ForneyLab with\nautomatic differentiation variational inference (ADVI) and Monte Carlo methods\nas implemented by state-of-the-art tools \"Edward\" and \"Stan\". In terms of\nperformance, extensibility and stability issues, ForneyLab appears to enjoy an\nedge relative to its competitors for automated inference in state-space models.","url_abs":"http://arxiv.org/abs/1811.03407v1","url_pdf":"http://arxiv.org/pdf/1811.03407v1.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":"a-factor-graph-approach-to-automated-design","repo_url":"https://github.com/biaslab/ForneyLab.jl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"},{"task_slug":"probabilistic-programming","task_name":"Probabilistic Programming"},{"task_slug":"state-space-models","task_name":"State Space Models"},{"task_slug":"variational-inference","task_name":"Variational Inference"},{"task_slug":"parameter-estimation","task_name":"parameter estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}