{"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/generalizing-hierarchical-bayesian-bandits","title":"Mixed-Effect Thompson Sampling","arxiv_id":"2205.15124","date":"2022-05-30","proceeding":null,"authors":["Imad Aouali","Branislav Kveton","Sumeet Katariya"],"abstract":"A contextual bandit is a popular framework for online learning to act under uncertainty. In practice, the number of actions is huge and their expected rewards are correlated. In this work, we introduce a general framework for capturing such correlations through a mixed-effect model where actions are related through multiple shared effect parameters. To explore efficiently using this structure, we propose Mixed-Effect Thompson Sampling (meTS) and bound its Bayes regret. The regret bound has two terms, one for learning the action parameters and the other for learning the shared effect parameters. The terms reflect the structure of our model and the quality of priors. Our theoretical findings are validated empirically using both synthetic and real-world problems. We also propose numerous extensions of practical interest. While they do not come with guarantees, they perform well empirically and show the generality of the proposed framework.","url_abs":"https://arxiv.org/abs/2205.15124v3","url_pdf":"https://arxiv.org/pdf/2205.15124v3.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":"generalizing-hierarchical-bayesian-bandits","repo_url":"https://github.com/imadaouali/mixed-effect-thompson-sampling","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"thompson-sampling","task_name":"Thompson Sampling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.15124","atlas_url":"https://app.syntology.ai/?focus=2205.15124","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.15124"}},"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/imadaouali/mixed-effect-thompson-sampling","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"52eab66d3ed18c96","entry":"evaluate","repo":"imadaouali/mixed-effect-thompson-sampling","repo_kind":"official","path":"bandits/evaluation.py","file_url":"https://github.com/imadaouali/mixed-effect-thompson-sampling/blob/HEAD/bandits/evaluation.py","link_basis":"harvester_set","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":"52eab66d3ed18c96"}},{"code_sha256_prefix":"abca9a6ba36d9e55","entry":"evaluate_one","repo":"imadaouali/mixed-effect-thompson-sampling","repo_kind":"official","path":"bandits/evaluation.py","file_url":"https://github.com/imadaouali/mixed-effect-thompson-sampling/blob/HEAD/bandits/evaluation.py","link_basis":"harvester_set","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":"abca9a6ba36d9e55"}},{"code_sha256_prefix":"585ebb12e503d2cc","entry":"linestyle2dashes","repo":"imadaouali/mixed-effect-thompson-sampling","repo_kind":"official","path":"utils/plotting.py","file_url":"https://github.com/imadaouali/mixed-effect-thompson-sampling/blob/HEAD/utils/plotting.py","link_basis":"harvester_set","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":"585ebb12e503d2cc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}