{"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/hyperparameter-optimization-a-spectral","title":"Hyperparameter Optimization: A Spectral Approach","arxiv_id":"1706.00764","date":"2017-06-02","proceeding":"ICLR 2018 1","authors":["Elad Hazan","Adam Klivans","Yang Yuan"],"abstract":"We give a simple, fast algorithm for hyperparameter optimization inspired by\ntechniques from the analysis of Boolean functions. We focus on the\nhigh-dimensional regime where the canonical example is training a neural\nnetwork with a large number of hyperparameters. The algorithm --- an iterative\napplication of compressed sensing techniques for orthogonal polynomials ---\nrequires only uniform sampling of the hyperparameters and is thus easily\nparallelizable.\n  Experiments for training deep neural networks on Cifar-10 show that compared\nto state-of-the-art tools (e.g., Hyperband and Spearmint), our algorithm finds\nsignificantly improved solutions, in some cases better than what is attainable\nby hand-tuning. In terms of overall running time (i.e., time required to sample\nvarious settings of hyperparameters plus additional computation time), we are\nat least an order of magnitude faster than Hyperband and Bayesian Optimization.\nWe also outperform Random Search 8x.\n  Additionally, our method comes with provable guarantees and yields the first\nimprovements on the sample complexity of learning decision trees in over two\ndecades. In particular, we obtain the first quasi-polynomial time algorithm for\nlearning noisy decision trees with polynomial sample complexity.","url_abs":"http://arxiv.org/abs/1706.00764v4","url_pdf":"http://arxiv.org/pdf/1706.00764v4.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":"hyperparameter-optimization-a-spectral","repo_url":"https://github.com/callowbird/Harmonica","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"bayesian-optimization","task_name":"Bayesian Optimization"},{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"},{"task_slug":"compressed-sensing","task_name":"compressed sensing"}],"methods":[{"method_slug":"random-search","method_name":"Random Search"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.00764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.00764"}},"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/callowbird/Harmonica","reach":null}],"summary":{"ran_fixture":2,"ran_honours":1},"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":"3ddcb3cf5b6faac6","entry":"batch_intermediate_sampling","repo":"callowbird/Harmonica","repo_kind":"official","path":"samplings.py","file_url":"https://github.com/callowbird/Harmonica/blob/HEAD/samplings.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ddcb3cf5b6faac6"}},{"code_sha256_prefix":"ff30c395a262d734","entry":"mask_random_sample","repo":"callowbird/Harmonica","repo_kind":"official","path":"samplings.py","file_url":"https://github.com/callowbird/Harmonica/blob/HEAD/samplings.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ff30c395a262d734"}},{"code_sha256_prefix":"7dc391fa0102351b","entry":"query","repo":"callowbird/Harmonica","repo_kind":"official","path":"samplings.py","file_url":"https://github.com/callowbird/Harmonica/blob/HEAD/samplings.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7dc391fa0102351b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}