{"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-transfer-across-developer-1","title":"Hyperparameter Transfer Across Developer Adjustments","arxiv_id":"2010.13117","date":"2020-10-25","proceeding":null,"authors":["Danny Stoll","Jörg K. H. Franke","Diane Wagner","Simon Selg","Frank Hutter"],"abstract":"After developer adjustments to a machine learning (ML) algorithm, how can the results of an old hyperparameter optimization (HPO) automatically be used to speedup a new HPO? This question poses a challenging problem, as developer adjustments can change which hyperparameter settings perform well, or even the hyperparameter search space itself. While many approaches exist that leverage knowledge obtained on previous tasks, so far, knowledge from previous development steps remains entirely untapped. In this work, we remedy this situation and propose a new research framework: hyperparameter transfer across adjustments (HT-AA). To lay a solid foundation for this research framework, we provide four simple HT-AA baseline algorithms and eight benchmarks changing various aspects of ML algorithms, their hyperparameter search spaces, and the neural architectures used. The best baseline, on average and depending on the budgets for the old and new HPO, reaches a given performance 1.2--2.6x faster than a prominent HPO algorithm without transfer. As HPO is a crucial step in ML development but requires extensive computational resources, this speedup would lead to faster development cycles, lower costs, and reduced environmental impacts. To make these benefits available to ML developers off-the-shelf and to facilitate future research on HT-AA, we provide python packages for our baselines and benchmarks.","url_abs":"https://arxiv.org/abs/2010.13117v1","url_pdf":"https://arxiv.org/pdf/2010.13117v1.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-transfer-across-developer-1","repo_url":"https://github.com/hp-transfer/htaa_experiments","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"}],"methods":[{"method_slug":"hpo","method_name":"HPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.13117","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.13117"}},"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/hp-transfer/htaa_experiments","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":"1f6163da7fae4d06","entry":"get_approach_data","repo":"hp-transfer/htaa_experiments","repo_kind":"official","path":"hp_transfer_aa_experiments/analyse/read_results.py","file_url":"https://github.com/hp-transfer/htaa_experiments/blob/HEAD/hp_transfer_aa_experiments/analyse/read_results.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":"1f6163da7fae4d06"}},{"code_sha256_prefix":"3a1d874f134ea66a","entry":"get_approach_spelling","repo":"hp-transfer/htaa_experiments","repo_kind":"official","path":"hp_transfer_aa_experiments/analyse/_plot_utils.py","file_url":"https://github.com/hp-transfer/htaa_experiments/blob/HEAD/hp_transfer_aa_experiments/analyse/_plot_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":"3a1d874f134ea66a"}},{"code_sha256_prefix":"3f3395554056249f","entry":"get_batch_result_row","repo":"hp-transfer/htaa_experiments","repo_kind":"official","path":"hp_transfer_aa_experiments/analyse/read_results.py","file_url":"https://github.com/hp-transfer/htaa_experiments/blob/HEAD/hp_transfer_aa_experiments/analyse/read_results.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":"3f3395554056249f"}},{"code_sha256_prefix":"91200aab3d16f1f6","entry":"get_benchmark_spelling","repo":"hp-transfer/htaa_experiments","repo_kind":"official","path":"hp_transfer_aa_experiments/analyse/_plot_utils.py","file_url":"https://github.com/hp-transfer/htaa_experiments/blob/HEAD/hp_transfer_aa_experiments/analyse/_plot_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":"91200aab3d16f1f6"}},{"code_sha256_prefix":"e781fa938a8428c6","entry":"get_runtype_spelling","repo":"hp-transfer/htaa_experiments","repo_kind":"official","path":"hp_transfer_aa_experiments/analyse/_plot_utils.py","file_url":"https://github.com/hp-transfer/htaa_experiments/blob/HEAD/hp_transfer_aa_experiments/analyse/_plot_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":"e781fa938a8428c6"}},{"code_sha256_prefix":"b2b38a78e92977b0","entry":"row_to_references","repo":"hp-transfer/htaa_experiments","repo_kind":"official","path":"hp_transfer_aa_experiments/analyse/compute_reference.py","file_url":"https://github.com/hp-transfer/htaa_experiments/blob/HEAD/hp_transfer_aa_experiments/analyse/compute_reference.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":"b2b38a78e92977b0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}