{"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/neural-thompson-sampling","title":"Neural Thompson Sampling","arxiv_id":"2010.00827","date":"2020-10-02","proceeding":"ICLR 2021 1","authors":["Weitong Zhang","Dongruo Zhou","Lihong Li","Quanquan Gu"],"abstract":"Thompson Sampling (TS) is one of the most effective algorithms for solving contextual multi-armed bandit problems. In this paper, we propose a new algorithm, called Neural Thompson Sampling, which adapts deep neural networks for both exploration and exploitation. At the core of our algorithm is a novel posterior distribution of the reward, where its mean is the neural network approximator, and its variance is built upon the neural tangent features of the corresponding neural network. We prove that, provided the underlying reward function is bounded, the proposed algorithm is guaranteed to achieve a cumulative regret of $\\mathcal{O}(T^{1/2})$, which matches the regret of other contextual bandit algorithms in terms of total round number $T$. Experimental comparisons with other benchmark bandit algorithms on various data sets corroborate our theory.","url_abs":"https://arxiv.org/abs/2010.00827v2","url_pdf":"https://arxiv.org/pdf/2010.00827v2.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":"neural-thompson-sampling","repo_url":"https://github.com/ZeroWeight/NeuralTS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"neural-thompson-sampling","repo_url":"https://github.com/RonyAbecidan/Neural-Thompson-Sampling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-armed-bandits","task_name":"Multi-Armed Bandits"},{"task_slug":"thompson-sampling","task_name":"Thompson Sampling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.00827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.00827"}},"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/RonyAbecidan/Neural-Thompson-Sampling","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZeroWeight/NeuralTS","reach":null}],"summary":{"ran":3,"ran_honours":2,"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":5,"ran":4,"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":7,"samples":[{"code_sha256_prefix":"c62f4329c658d771","entry":"Network","repo":"ZeroWeight/NeuralTS","repo_kind":"official","path":"learner_neural.py","file_url":"https://github.com/ZeroWeight/NeuralTS/blob/HEAD/learner_neural.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":"c62f4329c658d771"}},{"code_sha256_prefix":"69d982e24bbb5ea3","entry":"NeuralTS","repo":"ZeroWeight/NeuralTS","repo_kind":"official","path":"learner_neural.py","file_url":"https://github.com/ZeroWeight/NeuralTS/blob/HEAD/learner_neural.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":"69d982e24bbb5ea3"}},{"code_sha256_prefix":"503cf9bdb8ab553a","entry":"criterion","repo":"RonyAbecidan/Neural-Thompson-Sampling","repo_kind":"listed","path":"Experiments/NeuralTS.py","file_url":"https://github.com/RonyAbecidan/Neural-Thompson-Sampling/blob/HEAD/Experiments/NeuralTS.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"503cf9bdb8ab553a"}},{"code_sha256_prefix":"2a2738af58071535","entry":"flatten","repo":"RonyAbecidan/Neural-Thompson-Sampling","repo_kind":"listed","path":"Experiments/NeuralTS.py","file_url":"https://github.com/RonyAbecidan/Neural-Thompson-Sampling/blob/HEAD/Experiments/NeuralTS.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2a2738af58071535"}},{"code_sha256_prefix":"b1f4f9ee9551258d","entry":"get_theta","repo":"RonyAbecidan/Neural-Thompson-Sampling","repo_kind":"listed","path":"Experiments/NeuralTS.py","file_url":"https://github.com/RonyAbecidan/Neural-Thompson-Sampling/blob/HEAD/Experiments/NeuralTS.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b1f4f9ee9551258d"}},{"code_sha256_prefix":"12899114f3022a68","entry":"transform","repo":"RonyAbecidan/Neural-Thompson-Sampling","repo_kind":"listed","path":"Experiments/NeuralTS.py","file_url":"https://github.com/RonyAbecidan/Neural-Thompson-Sampling/blob/HEAD/Experiments/NeuralTS.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"12899114f3022a68"}},{"code_sha256_prefix":"8610c2168fca08ee","entry":"NeuralTS","repo":"RonyAbecidan/Neural-Thompson-Sampling","repo_kind":"listed","path":"Experiments/NeuralTS.py","file_url":"https://github.com/RonyAbecidan/Neural-Thompson-Sampling/blob/HEAD/Experiments/NeuralTS.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":"8610c2168fca08ee"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}