{"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-bayesian-neural-networks-robust","title":"Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning","arxiv_id":"1907.00865","date":"2019-07-01","proceeding":null,"authors":["Sebastian Farquhar","Michael Osborne","Yarin Gal"],"abstract":"We propose Radial Bayesian Neural Networks (BNNs): a variational approximate posterior for BNNs which scales well to large models while maintaining a distribution over weight-space with full support. Other scalable Bayesian deep learning methods, like MC dropout or deep ensembles, have discrete support-they assign zero probability to almost all of the weight-space. Unlike these discrete support methods, Radial BNNs' full support makes them suitable for use as a prior for sequential inference. In addition, they solve the conceptual challenges with the a priori implausibility of weight distributions with discrete support. The Radial BNN is motivated by avoiding a sampling problem in 'mean-field' variational inference (MFVI) caused by the so-called 'soap-bubble' pathology of multivariate Gaussians. We show that, unlike MFVI, Radial BNNs are robust to hyperparameters and can be efficiently applied to a challenging real-world medical application without needing ad-hoc tweaks and intensive tuning. In fact, in this setting Radial BNNs out-perform discrete-support methods like MC dropout. Lastly, by using Radial BNNs as a theoretically principled, robust alternative to MFVI we make significant strides in a Bayesian continual learning evaluation.","url_abs":"https://arxiv.org/abs/1907.00865v4","url_pdf":"https://arxiv.org/pdf/1907.00865v4.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-bayesian-neural-networks-robust","repo_url":"https://github.com/SebFar/radial_bnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"radial-bayesian-neural-networks-robust","repo_url":"https://github.com/IntelLabs/bayesian-torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"radial-bayesian-neural-networks-robust","repo_url":"https://github.com/danielkelshaw/RadialBNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"radial-bayesian-neural-networks-robust","repo_url":"https://github.com/danielkelshaw/WeightUncertainty","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1907.00865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.00865"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/danielkelshaw/WeightUncertainty","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/danielkelshaw/RadialBNN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IntelLabs/bayesian-torch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SebFar/radial_bnn","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":11},"by_repo_kind":{"official":{"samples":8,"ran":0,"repositories":1},"listed":{"samples":2,"ran":0,"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":2,"samples":[{"code_sha256_prefix":"bdea437fe2c544f2","entry":"test","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"bdea437fe2c544f2"}},{"code_sha256_prefix":"c19d25b8c77aa68b","entry":"accuracy","repo":"SebFar/radial_bnn","repo_kind":"official","path":"model/metric.py","file_url":"https://github.com/SebFar/radial_bnn/blob/HEAD/model/metric.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c19d25b8c77aa68b"}},{"code_sha256_prefix":"fd559b979213c51f","entry":"binary_accuracy","repo":"SebFar/radial_bnn","repo_kind":"official","path":"model/metric.py","file_url":"https://github.com/SebFar/radial_bnn/blob/HEAD/model/metric.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd559b979213c51f"}},{"code_sha256_prefix":"b1bd3bfd82f68116","entry":"ensure_dir","repo":"SebFar/radial_bnn","repo_kind":"official","path":"utils/util.py","file_url":"https://github.com/SebFar/radial_bnn/blob/HEAD/utils/util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b1bd3bfd82f68116"}},{"code_sha256_prefix":"49604c979a400d49","entry":"gaussian","repo":"SebFar/radial_bnn","repo_kind":"official","path":"radial_layers/distributions.py","file_url":"https://github.com/SebFar/radial_bnn/blob/HEAD/radial_layers/distributions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"49604c979a400d49"}},{"code_sha256_prefix":"78d9b6bfcfa64f7b","entry":"gaussian_prior","repo":"SebFar/radial_bnn","repo_kind":"official","path":"radial_layers/distributions.py","file_url":"https://github.com/SebFar/radial_bnn/blob/HEAD/radial_layers/distributions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"78d9b6bfcfa64f7b"}},{"code_sha256_prefix":"bcf702b12b523972","entry":"manage_seed","repo":"SebFar/radial_bnn","repo_kind":"official","path":"utils/util.py","file_url":"https://github.com/SebFar/radial_bnn/blob/HEAD/utils/util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bcf702b12b523972"}},{"code_sha256_prefix":"4bd0281f4f8ca587","entry":"minibatch_weight","repo":"danielkelshaw/WeightUncertainty","repo_kind":"listed","path":"torchwu/utils/minibatch_weighting.py","file_url":"https://github.com/danielkelshaw/WeightUncertainty/blob/HEAD/torchwu/utils/minibatch_weighting.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4bd0281f4f8ca587"}},{"code_sha256_prefix":"792b7ca7eb639fd4","entry":"radial","repo":"SebFar/radial_bnn","repo_kind":"official","path":"radial_layers/distributions.py","file_url":"https://github.com/SebFar/radial_bnn/blob/HEAD/radial_layers/distributions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"792b7ca7eb639fd4"}},{"code_sha256_prefix":"5cc87715e60867cd","entry":"train","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"5cc87715e60867cd"}},{"code_sha256_prefix":"4d5c237d1e21d9d8","entry":"variational_accuracy","repo":"SebFar/radial_bnn","repo_kind":"official","path":"model/metric.py","file_url":"https://github.com/SebFar/radial_bnn/blob/HEAD/model/metric.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d5c237d1e21d9d8"}},{"code_sha256_prefix":"c220fcf8b0df7302","entry":"variational_approximator","repo":"danielkelshaw/WeightUncertainty","repo_kind":"listed","path":"torchwu/utils/variational_approximator.py","file_url":"https://github.com/danielkelshaw/WeightUncertainty/blob/HEAD/torchwu/utils/variational_approximator.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c220fcf8b0df7302"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}