{"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/learning-to-learn-with-generative-models-of","title":"Learning to Learn with Generative Models of Neural Network Checkpoints","arxiv_id":"2209.12892","date":"2022-09-26","proceeding":null,"authors":["William Peebles","Ilija Radosavovic","Tim Brooks","Alexei A. Efros","Jitendra Malik"],"abstract":"We explore a data-driven approach for learning to optimize neural networks. We construct a dataset of neural network checkpoints and train a generative model on the parameters. In particular, our model is a conditional diffusion transformer that, given an initial input parameter vector and a prompted loss, error, or return, predicts the distribution over parameter updates that achieve the desired metric. At test time, it can optimize neural networks with unseen parameters for downstream tasks in just one update. We find that our approach successfully generates parameters for a wide range of loss prompts. Moreover, it can sample multimodal parameter solutions and has favorable scaling properties. We apply our method to different neural network architectures and tasks in supervised and reinforcement learning.","url_abs":"https://arxiv.org/abs/2209.12892v1","url_pdf":"https://arxiv.org/pdf/2209.12892v1.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":"learning-to-learn-with-generative-models-of","repo_url":"https://github.com/wpeebles/g.pt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.12892","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.12892"}},"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/wpeebles/g.pt","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"ran":2,"ran_fixture":1,"unverified":17},"by_repo_kind":{"official":{"samples":20,"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":"d160a205c24a70f9","entry":"color_norm","repo":"wpeebles/g.pt","repo_kind":"official","path":"data_gen/train_cifar10.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/data_gen/train_cifar10.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d160a205c24a70f9"}},{"code_sha256_prefix":"803bcd86e3301891","entry":"time_string","repo":"wpeebles/g.pt","repo_kind":"official","path":"Gpt/meters.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/Gpt/meters.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"803bcd86e3301891"}},{"code_sha256_prefix":"8e712c383c677282","entry":"zero_pad","repo":"wpeebles/g.pt","repo_kind":"official","path":"data_gen/train_cifar10.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/data_gen/train_cifar10.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"8e712c383c677282"}},{"code_sha256_prefix":"250494257e1f8188","entry":"all_gather","repo":"wpeebles/g.pt","repo_kind":"official","path":"Gpt/distributed.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/Gpt/distributed.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"250494257e1f8188"}},{"code_sha256_prefix":"7bef924189a2a628","entry":"construct_loader","repo":"wpeebles/g.pt","repo_kind":"official","path":"Gpt/utils.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/Gpt/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"7bef924189a2a628"}},{"code_sha256_prefix":"337c2966cca20001","entry":"construct_loader","repo":"wpeebles/g.pt","repo_kind":"official","path":"data_gen/train_mnist.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/data_gen/train_mnist.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"337c2966cca20001"}},{"code_sha256_prefix":"9759670b96772cd5","entry":"create_thresholding_fn","repo":"wpeebles/g.pt","repo_kind":"official","path":"Gpt/vis.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/Gpt/vis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"9759670b96772cd5"}},{"code_sha256_prefix":"06ebeb225cfdc4a0","entry":"ddim_synth","repo":"wpeebles/g.pt","repo_kind":"official","path":"playground.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/playground.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"06ebeb225cfdc4a0"}},{"code_sha256_prefix":"9817cd76b1cffb0c","entry":"dump_json_stats","repo":"wpeebles/g.pt","repo_kind":"official","path":"Gpt/meters.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/Gpt/meters.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"9817cd76b1cffb0c"}},{"code_sha256_prefix":"5c827254b86e623d","entry":"eta_str","repo":"wpeebles/g.pt","repo_kind":"official","path":"data_gen/train_mnist.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/data_gen/train_mnist.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"5c827254b86e623d"}},{"code_sha256_prefix":"ed27fb884352e87a","entry":"float_to_decimal","repo":"wpeebles/g.pt","repo_kind":"official","path":"Gpt/meters.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/Gpt/meters.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ed27fb884352e87a"}},{"code_sha256_prefix":"1cd4047c59310f59","entry":"horizontal_flip","repo":"wpeebles/g.pt","repo_kind":"official","path":"data_gen/train_cifar10.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/data_gen/train_cifar10.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"1cd4047c59310f59"}},{"code_sha256_prefix":"13bc2d293163e97b","entry":"is_main_proc","repo":"wpeebles/g.pt","repo_kind":"official","path":"Gpt/distributed.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/Gpt/distributed.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"13bc2d293163e97b"}},{"code_sha256_prefix":"3beb27a8d68b5a5e","entry":"lr_fun_cos","repo":"wpeebles/g.pt","repo_kind":"official","path":"Gpt/utils.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/Gpt/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"3beb27a8d68b5a5e"}},{"code_sha256_prefix":"a45c474751d02fe9","entry":"scaled_all_reduce","repo":"wpeebles/g.pt","repo_kind":"official","path":"Gpt/distributed.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/Gpt/distributed.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a45c474751d02fe9"}},{"code_sha256_prefix":"6f53e4795c83768e","entry":"setup_env","repo":"wpeebles/g.pt","repo_kind":"official","path":"Gpt/utils.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/Gpt/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"6f53e4795c83768e"}},{"code_sha256_prefix":"c2e26f19600bfc6a","entry":"slerp","repo":"wpeebles/g.pt","repo_kind":"official","path":"Gpt/latent_walk_helpers.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/Gpt/latent_walk_helpers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c2e26f19600bfc6a"}},{"code_sha256_prefix":"d06e1fd0a7f317f7","entry":"slerpify","repo":"wpeebles/g.pt","repo_kind":"official","path":"Gpt/latent_walk_helpers.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/Gpt/latent_walk_helpers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d06e1fd0a7f317f7"}},{"code_sha256_prefix":"8c81a09dfbb6d408","entry":"synth","repo":"wpeebles/g.pt","repo_kind":"official","path":"Gpt/vis.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/Gpt/vis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"8c81a09dfbb6d408"}},{"code_sha256_prefix":"093a895f2d9c1921","entry":"top1_error","repo":"wpeebles/g.pt","repo_kind":"official","path":"data_gen/train_mnist.py","file_url":"https://github.com/wpeebles/g.pt/blob/HEAD/data_gen/train_mnist.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"093a895f2d9c1921"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}