{"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/radial-and-directional-posteriors-for","title":"Radial and Directional Posteriors for Bayesian Neural Networks","arxiv_id":"1902.02603","date":"2019-02-07","proceeding":null,"authors":["Changyong Oh","Kamil Adamczewski","Mijung Park"],"abstract":"We propose a new variational family for Bayesian neural networks. We\ndecompose the variational posterior into two components, where the radial\ncomponent captures the strength of each neuron in terms of its magnitude; while\nthe directional component captures the statistical dependencies among the\nweight parameters. The dependencies learned via the directional density provide\nbetter modeling performance compared to the widely-used Gaussian\nmean-field-type variational family. In addition, the strength of input and\noutput neurons learned via the radial density provides a structured way to\ncompress neural networks. Indeed, experiments show that our variational family\nimproves predictive performance and yields compressed networks simultaneously.","url_abs":"http://arxiv.org/abs/1902.02603v2","url_pdf":"http://arxiv.org/pdf/1902.02603v2.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":"radial-and-directional-posteriors-for","repo_url":"https://github.com/ChangYong-Oh/RadiusDirectionPosteriors","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"radial-and-directional-posteriors-for","repo_url":"https://github.com/JRConti/Bessel-functions-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1902.02603","atlas_url":"https://app.syntology.ai/?focus=1902.02603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.02603"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ChangYong-Oh/RadiusDirectionPosteriors","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JRConti/Bessel-functions-Pytorch","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"bdab7af08bcc2f37","entry":"train","repo":"ChangYong-Oh/RadiusDirectionPosteriors","repo_kind":"official","path":"RadiusDirectionPosteriors/train_double_uci.py","file_url":"https://github.com/ChangYong-Oh/RadiusDirectionPosteriors/blob/HEAD/RadiusDirectionPosteriors/train_double_uci.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bdab7af08bcc2f37"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}