{"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/using-large-language-models-for","title":"Using Large Language Models for Hyperparameter Optimization","arxiv_id":"2312.04528","date":"2023-12-07","proceeding":null,"authors":["Michael R. Zhang","Nishkrit Desai","Juhan Bae","Jonathan Lorraine","Jimmy Ba"],"abstract":"This paper explores the use of foundational large language models (LLMs) in hyperparameter optimization (HPO). Hyperparameters are critical in determining the effectiveness of machine learning models, yet their optimization often relies on manual approaches in limited-budget settings. By prompting LLMs with dataset and model descriptions, we develop a methodology where LLMs suggest hyperparameter configurations, which are iteratively refined based on model performance. Our empirical evaluations on standard benchmarks reveal that within constrained search budgets, LLMs can match or outperform traditional HPO methods like Bayesian optimization across different models on standard benchmarks. Furthermore, we propose to treat the code specifying our model as a hyperparameter, which the LLM outputs and affords greater flexibility than existing HPO approaches.","url_abs":"https://arxiv.org/abs/2312.04528v2","url_pdf":"https://arxiv.org/pdf/2312.04528v2.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":"using-large-language-models-for","repo_url":"https://github.com/michaelrzhang/llm-hyperopt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"bayesian-optimization","task_name":"Bayesian Optimization"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"}],"methods":[{"method_slug":"hpo","method_name":"HPO"},{"method_slug":"random-search","method_name":"Random Search"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.04528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04528"}},"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/michaelrzhang/llm-hyperopt","reach":{"status":"ok"}}],"summary":{"ran":2,"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"cc66dbe7af8469d1","entry":"get_function","repo":"michaelrzhang/llm-hyperopt","repo_kind":"official","path":"utils/toy_utils.py","file_url":"https://github.com/michaelrzhang/llm-hyperopt/blob/HEAD/utils/toy_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":"cc66dbe7af8469d1"}},{"code_sha256_prefix":"fa90fe6d27baea6b","entry":"get_function_name","repo":"michaelrzhang/llm-hyperopt","repo_kind":"official","path":"utils/toy_utils.py","file_url":"https://github.com/michaelrzhang/llm-hyperopt/blob/HEAD/utils/toy_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":"fa90fe6d27baea6b"}},{"code_sha256_prefix":"6ba8cee9f5daea41","entry":"pair","repo":"michaelrzhang/llm-hyperopt","repo_kind":"official","path":"cifar/vit.py","file_url":"https://github.com/michaelrzhang/llm-hyperopt/blob/HEAD/cifar/vit.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ba8cee9f5daea41"}},{"code_sha256_prefix":"747fbaa891c47810","entry":"get_cifar10_dataset","repo":"michaelrzhang/llm-hyperopt","repo_kind":"official","path":"cifar/pipeline.py","file_url":"https://github.com/michaelrzhang/llm-hyperopt/blob/HEAD/cifar/pipeline.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":"747fbaa891c47810"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}