{"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/subspace-inference-for-bayesian-deep-learning","title":"Subspace Inference for Bayesian Deep Learning","arxiv_id":"1907.07504","date":"2019-07-17","proceeding":null,"authors":["Pavel Izmailov","Wesley J. Maddox","Polina Kirichenko","Timur Garipov","Dmitry Vetrov","Andrew Gordon Wilson"],"abstract":"Bayesian inference was once a gold standard for learning with neural networks, providing accurate full predictive distributions and well calibrated uncertainty. However, scaling Bayesian inference techniques to deep neural networks is challenging due to the high dimensionality of the parameter space. In this paper, we construct low-dimensional subspaces of parameter space, such as the first principal components of the stochastic gradient descent (SGD) trajectory, which contain diverse sets of high performing models. In these subspaces, we are able to apply elliptical slice sampling and variational inference, which struggle in the full parameter space. We show that Bayesian model averaging over the induced posterior in these subspaces produces accurate predictions and well calibrated predictive uncertainty for both regression and image classification.","url_abs":"https://arxiv.org/abs/1907.07504v1","url_pdf":"https://arxiv.org/pdf/1907.07504v1.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":"subspace-inference-for-bayesian-deep-learning","repo_url":"https://github.com/wjmaddox/drbayes","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"variational-inference","task_name":"Variational Inference"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1907.07504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.07504"}},"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/wjmaddox/drbayes","reach":null}],"summary":{"ran_fixture":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"36b53181e3081833","entry":"elliptical_slice","repo":"wjmaddox/drbayes","repo_kind":"official","path":"subspace_inference/posteriors/elliptical_slice.py","file_url":"https://github.com/wjmaddox/drbayes/blob/HEAD/subspace_inference/posteriors/elliptical_slice.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"36b53181e3081833"}},{"code_sha256_prefix":"5468f8d7bb560ad8","entry":"nll","repo":"wjmaddox/drbayes","repo_kind":"official","path":"experiments/cifar_exps/subspace_ess.py","file_url":"https://github.com/wjmaddox/drbayes/blob/HEAD/experiments/cifar_exps/subspace_ess.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"5468f8d7bb560ad8"}},{"code_sha256_prefix":"52ba2e852ea3a885","entry":"slice_sample","repo":"wjmaddox/drbayes","repo_kind":"official","path":"subspace_inference/posteriors/elliptical_slice.py","file_url":"https://github.com/wjmaddox/drbayes/blob/HEAD/subspace_inference/posteriors/elliptical_slice.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"52ba2e852ea3a885"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}