{"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/stochastic-hyperparameter-optimization","title":"Stochastic Hyperparameter Optimization through Hypernetworks","arxiv_id":"1802.09419","date":"2018-02-26","proceeding":"ICLR 2018 1","authors":["Jonathan Lorraine","David Duvenaud"],"abstract":"Machine learning models are often tuned by nesting optimization of model\nweights inside the optimization of hyperparameters. We give a method to\ncollapse this nested optimization into joint stochastic optimization of weights\nand hyperparameters. Our process trains a neural network to output\napproximately optimal weights as a function of hyperparameters. We show that\nour technique converges to locally optimal weights and hyperparameters for\nsufficiently large hypernetworks. We compare this method to standard\nhyperparameter optimization strategies and demonstrate its effectiveness for\ntuning thousands of hyperparameters.","url_abs":"http://arxiv.org/abs/1802.09419v2","url_pdf":"http://arxiv.org/pdf/1802.09419v2.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":"stochastic-hyperparameter-optimization","repo_url":"https://github.com/lorraine2/hypernet-hypertraining","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"},{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"}],"methods":[{"method_slug":"hypernetwork","method_name":"HyperNetwork"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1802.09419","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.09419"}},"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/lorraine2/hypernet-hypertraining","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":11},"by_repo_kind":{"listed":{"samples":11,"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":"ee2f9c951a3f0a07","entry":"adam","repo":"lorraine2/hypernet-hypertraining","repo_kind":"listed","path":"code/optimizers.py","file_url":"https://github.com/lorraine2/hypernet-hypertraining/blob/HEAD/code/optimizers.py","link_basis":"harvester_set","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":"ee2f9c951a3f0a07"}},{"code_sha256_prefix":"69d2f57c7e093831","entry":"best_response","repo":"lorraine2/hypernet-hypertraining","repo_kind":"listed","path":"code/loss_manifold.py","file_url":"https://github.com/lorraine2/hypernet-hypertraining/blob/HEAD/code/loss_manifold.py","link_basis":"harvester_set","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":"69d2f57c7e093831"}},{"code_sha256_prefix":"9c2a23e40c56bf52","entry":"create_figure_and_axs","repo":"lorraine2/hypernet-hypertraining","repo_kind":"listed","path":"code/plotting.py","file_url":"https://github.com/lorraine2/hypernet-hypertraining/blob/HEAD/code/plotting.py","link_basis":"harvester_set","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":"9c2a23e40c56bf52"}},{"code_sha256_prefix":"f4b5a0d4c2bb9340","entry":"full_extent","repo":"lorraine2/hypernet-hypertraining","repo_kind":"listed","path":"code/plotting.py","file_url":"https://github.com/lorraine2/hypernet-hypertraining/blob/HEAD/code/plotting.py","link_basis":"harvester_set","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":"f4b5a0d4c2bb9340"}},{"code_sha256_prefix":"efd23da01a3364b1","entry":"identity","repo":"lorraine2/hypernet-hypertraining","repo_kind":"listed","path":"code/neural_network.py","file_url":"https://github.com/lorraine2/hypernet-hypertraining/blob/HEAD/code/neural_network.py","link_basis":"harvester_set","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":"efd23da01a3364b1"}},{"code_sha256_prefix":"6c7099b9362c9e4e","entry":"init_random_params","repo":"lorraine2/hypernet-hypertraining","repo_kind":"listed","path":"code/neural_network.py","file_url":"https://github.com/lorraine2/hypernet-hypertraining/blob/HEAD/code/neural_network.py","link_basis":"harvester_set","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":"6c7099b9362c9e4e"}},{"code_sha256_prefix":"33654d7c183a991c","entry":"log_gaussian","repo":"lorraine2/hypernet-hypertraining","repo_kind":"listed","path":"code/learn_vs_true_loss_scatter.py","file_url":"https://github.com/lorraine2/hypernet-hypertraining/blob/HEAD/code/learn_vs_true_loss_scatter.py","link_basis":"harvester_set","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":"33654d7c183a991c"}},{"code_sha256_prefix":"e037e68de30ee470","entry":"opt_params","repo":"lorraine2/hypernet-hypertraining","repo_kind":"listed","path":"code/optimizers.py","file_url":"https://github.com/lorraine2/hypernet-hypertraining/blob/HEAD/code/optimizers.py","link_basis":"harvester_set","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":"e037e68de30ee470"}},{"code_sha256_prefix":"76060568553562d9","entry":"orthogonal_proj","repo":"lorraine2/hypernet-hypertraining","repo_kind":"listed","path":"code/loss_manifold.py","file_url":"https://github.com/lorraine2/hypernet-hypertraining/blob/HEAD/code/loss_manifold.py","link_basis":"harvester_set","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":"76060568553562d9"}},{"code_sha256_prefix":"57d85d9dbc47f39e","entry":"relu","repo":"lorraine2/hypernet-hypertraining","repo_kind":"listed","path":"code/neural_network.py","file_url":"https://github.com/lorraine2/hypernet-hypertraining/blob/HEAD/code/neural_network.py","link_basis":"harvester_set","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":"57d85d9dbc47f39e"}},{"code_sha256_prefix":"a3486434b5aed9e0","entry":"train_loss_fun","repo":"lorraine2/hypernet-hypertraining","repo_kind":"listed","path":"code/loss_manifold.py","file_url":"https://github.com/lorraine2/hypernet-hypertraining/blob/HEAD/code/loss_manifold.py","link_basis":"harvester_set","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":"a3486434b5aed9e0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}