{"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/temperature-optimization-for-bayesian-deep","title":"Temperature Optimization for Bayesian Deep Learning","arxiv_id":"2410.05757","date":"2024-10-08","proceeding":null,"authors":["Kenyon Ng","Chris van der Heide","Liam Hodgkinson","Susan Wei"],"abstract":"The Cold Posterior Effect (CPE) is a phenomenon in Bayesian Deep Learning (BDL), where tempering the posterior to a cold temperature often improves the predictive performance of the posterior predictive distribution (PPD). Although the term `CPE' suggests colder temperatures are inherently better, the BDL community increasingly recognizes that this is not always the case. Despite this, there remains no systematic method for finding the optimal temperature beyond grid search. In this work, we propose a data-driven approach to select the temperature that maximizes test log-predictive density, treating the temperature as a model parameter and estimating it directly from the data. We empirically demonstrate that our method performs comparably to grid search, at a fraction of the cost, across both regression and classification tasks. Finally, we highlight the differing perspectives on CPE between the BDL and Generalized Bayes communities: while the former primarily emphasizes the predictive performance of the PPD, the latter prioritizes the utility of the posterior under model misspecification; these distinct objectives lead to different temperature preferences.","url_abs":"https://arxiv.org/abs/2410.05757v2","url_pdf":"https://arxiv.org/pdf/2410.05757v2.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":"temperature-optimization-for-bayesian-deep","repo_url":"https://github.com/weiyaw/tempered-posteriors","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[{"method_slug":"cpe","method_name":"CPE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.05757","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05757"}},"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/weiyaw/tempered-posteriors","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":11,"unverified":4},"by_repo_kind":{"official":{"samples":15,"ran":11,"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":"9b436ef2d0792040","entry":"add_classficiation","repo":"weiyaw/tempered-posteriors","repo_kind":"official","path":"datasets/download_data.py","file_url":"https://github.com/weiyaw/tempered-posteriors/blob/HEAD/datasets/download_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9b436ef2d0792040"}},{"code_sha256_prefix":"5cadf1fc3261f6c0","entry":"add_regression","repo":"weiyaw/tempered-posteriors","repo_kind":"official","path":"datasets/download_data.py","file_url":"https://github.com/weiyaw/tempered-posteriors/blob/HEAD/datasets/download_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5cadf1fc3261f6c0"}},{"code_sha256_prefix":"52941c123cdcadee","entry":"filter_args","repo":"weiyaw/tempered-posteriors","repo_kind":"official","path":"inference.py","file_url":"https://github.com/weiyaw/tempered-posteriors/blob/HEAD/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"52941c123cdcadee"}},{"code_sha256_prefix":"ad3ede600b6e930f","entry":"flatdict","repo":"weiyaw/tempered-posteriors","repo_kind":"official","path":"main-empirical.py","file_url":"https://github.com/weiyaw/tempered-posteriors/blob/HEAD/main-empirical.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ad3ede600b6e930f"}},{"code_sha256_prefix":"0d4d5d0d375201d6","entry":"is_numeric","repo":"weiyaw/tempered-posteriors","repo_kind":"official","path":"training.py","file_url":"https://github.com/weiyaw/tempered-posteriors/blob/HEAD/training.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d4d5d0d375201d6"}},{"code_sha256_prefix":"2afc2e44e4aa1fe0","entry":"log_prob_tree","repo":"weiyaw/tempered-posteriors","repo_kind":"official","path":"training.py","file_url":"https://github.com/weiyaw/tempered-posteriors/blob/HEAD/training.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2afc2e44e4aa1fe0"}},{"code_sha256_prefix":"1910403f272fdc73","entry":"make_constant_lr_schedule_with_cosine_burnin","repo":"weiyaw/tempered-posteriors","repo_kind":"official","path":"sgmcmc.py","file_url":"https://github.com/weiyaw/tempered-posteriors/blob/HEAD/sgmcmc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1910403f272fdc73"}},{"code_sha256_prefix":"013661d041de5d86","entry":"make_cosine_schedule","repo":"weiyaw/tempered-posteriors","repo_kind":"official","path":"sgmcmc.py","file_url":"https://github.com/weiyaw/tempered-posteriors/blob/HEAD/sgmcmc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"013661d041de5d86"}},{"code_sha256_prefix":"cba0faabe1fa7dc7","entry":"normalize","repo":"weiyaw/tempered-posteriors","repo_kind":"official","path":"datasets/download_data.py","file_url":"https://github.com/weiyaw/tempered-posteriors/blob/HEAD/datasets/download_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cba0faabe1fa7dc7"}},{"code_sha256_prefix":"67ca4f13b861a952","entry":"read_from_local","repo":"weiyaw/tempered-posteriors","repo_kind":"official","path":"utils.py","file_url":"https://github.com/weiyaw/tempered-posteriors/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"67ca4f13b861a952"}},{"code_sha256_prefix":"536d78b9441ea597","entry":"sample_X_grid","repo":"weiyaw/tempered-posteriors","repo_kind":"official","path":"data.py","file_url":"https://github.com/weiyaw/tempered-posteriors/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"536d78b9441ea597"}},{"code_sha256_prefix":"b18d120529093966","entry":"calc_normal_logprob_resid","repo":"weiyaw/tempered-posteriors","repo_kind":"official","path":"metrics.py","file_url":"https://github.com/weiyaw/tempered-posteriors/blob/HEAD/metrics.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":"b18d120529093966"}},{"code_sha256_prefix":"91345e63f4999e0e","entry":"flatten_dict","repo":"weiyaw/tempered-posteriors","repo_kind":"official","path":"visual_utils.py","file_url":"https://github.com/weiyaw/tempered-posteriors/blob/HEAD/visual_utils.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":"91345e63f4999e0e"}},{"code_sha256_prefix":"bace351d40c0081c","entry":"normal_like_tree","repo":"weiyaw/tempered-posteriors","repo_kind":"official","path":"sgmcmc.py","file_url":"https://github.com/weiyaw/tempered-posteriors/blob/HEAD/sgmcmc.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":"bace351d40c0081c"}},{"code_sha256_prefix":"ee368fc45143d54a","entry":"sample_tree","repo":"weiyaw/tempered-posteriors","repo_kind":"official","path":"data.py","file_url":"https://github.com/weiyaw/tempered-posteriors/blob/HEAD/data.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":"ee368fc45143d54a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}