{"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/active-learning-with-fully-bayesian-neural","title":"Active Learning with Fully Bayesian Neural Networks for Discontinuous and Nonstationary Data","arxiv_id":"2405.09817","date":"2024-05-16","proceeding":null,"authors":["Maxim Ziatdinov"],"abstract":"Active learning optimizes the exploration of large parameter spaces by strategically selecting which experiments or simulations to conduct, thus reducing resource consumption and potentially accelerating scientific discovery. A key component of this approach is a probabilistic surrogate model, typically a Gaussian Process (GP), which approximates an unknown functional relationship between control parameters and a target property. However, conventional GPs often struggle when applied to systems with discontinuities and non-stationarities, prompting the exploration of alternative models. This limitation becomes particularly relevant in physical science problems, which are often characterized by abrupt transitions between different system states and rapid changes in physical property behavior. Fully Bayesian Neural Networks (FBNNs) serve as a promising substitute, treating all neural network weights probabilistically and leveraging advanced Markov Chain Monte Carlo techniques for direct sampling from the posterior distribution. This approach enables FBNNs to provide reliable predictive distributions, crucial for making informed decisions under uncertainty in the active learning setting. Although traditionally considered too computationally expensive for 'big data' applications, many physical sciences problems involve small amounts of data in relatively low-dimensional parameter spaces. Here, we assess the suitability and performance of FBNNs with the No-U-Turn Sampler for active learning tasks in the 'small data' regime, highlighting their potential to enhance predictive accuracy and reliability on test functions relevant to problems in physical sciences.","url_abs":"https://arxiv.org/abs/2405.09817v2","url_pdf":"https://arxiv.org/pdf/2405.09817v2.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":"active-learning-with-fully-bayesian-neural","repo_url":"https://github.com/ziatdinovmax/neurobayes","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"scientific-discovery","task_name":"scientific discovery"}],"methods":[{"method_slug":"gps","method_name":"GPS"},{"method_slug":"gaussian-process","method_name":"Gaussian Process"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2405.09817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.09817"}},"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/ziatdinovmax/neurobayes","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":5},"by_repo_kind":{"official":{"samples":8,"ran":3,"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":8,"samples":[{"code_sha256_prefix":"9973f56126fb76b2","entry":"create_swa_schedule","repo":"ziatdinovmax/neurobayes","repo_kind":"official","path":"neurobayes/flax_nets/train_utils.py","file_url":"https://github.com/ziatdinovmax/neurobayes/blob/HEAD/neurobayes/flax_nets/train_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9973f56126fb76b2"}},{"code_sha256_prefix":"1a536ce2d2d086cb","entry":"get_conv_and_pool_ops","repo":"ziatdinovmax/neurobayes","repo_kind":"official","path":"neurobayes/flax_nets/convnet.py","file_url":"https://github.com/ziatdinovmax/neurobayes/blob/HEAD/neurobayes/flax_nets/convnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1a536ce2d2d086cb"}},{"code_sha256_prefix":"d7a49aa7e1c50a27","entry":"select_bayesian_attention_weights","repo":"ziatdinovmax/neurobayes","repo_kind":"official","path":"neurobayes/flax_nets/parameter_selection.py","file_url":"https://github.com/ziatdinovmax/neurobayes/blob/HEAD/neurobayes/flax_nets/parameter_selection.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d7a49aa7e1c50a27"}},{"code_sha256_prefix":"c492046e0fb558f0","entry":"get_configs","repo":"ziatdinovmax/neurobayes","repo_kind":"official","path":"neurobayes/flax_nets/config_utils.py","file_url":"https://github.com/ziatdinovmax/neurobayes/blob/HEAD/neurobayes/flax_nets/config_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c492046e0fb558f0"}},{"code_sha256_prefix":"7ec0a34ac86d15d5","entry":"select_bayesian_weights","repo":"ziatdinovmax/neurobayes","repo_kind":"official","path":"neurobayes/flax_nets/parameter_selection.py","file_url":"https://github.com/ziatdinovmax/neurobayes/blob/HEAD/neurobayes/flax_nets/parameter_selection.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7ec0a34ac86d15d5"}},{"code_sha256_prefix":"e8698697f702e59d","entry":"select_bayesian_weights_conv","repo":"ziatdinovmax/neurobayes","repo_kind":"official","path":"neurobayes/flax_nets/parameter_selection.py","file_url":"https://github.com/ziatdinovmax/neurobayes/blob/HEAD/neurobayes/flax_nets/parameter_selection.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e8698697f702e59d"}},{"code_sha256_prefix":"fe418943e300e241","entry":"split_mlp","repo":"ziatdinovmax/neurobayes","repo_kind":"official","path":"neurobayes/flax_nets/splitter.py","file_url":"https://github.com/ziatdinovmax/neurobayes/blob/HEAD/neurobayes/flax_nets/splitter.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fe418943e300e241"}},{"code_sha256_prefix":"aee9949ab926e176","entry":"split_mlp2head","repo":"ziatdinovmax/neurobayes","repo_kind":"official","path":"neurobayes/flax_nets/splitter.py","file_url":"https://github.com/ziatdinovmax/neurobayes/blob/HEAD/neurobayes/flax_nets/splitter.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aee9949ab926e176"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}