{"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/evograd-efficient-gradient-based-meta","title":"EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization","arxiv_id":"2106.10575","date":"2021-06-19","proceeding":"NeurIPS 2021 12","authors":["Ondrej Bohdal","Yongxin Yang","Timothy Hospedales"],"abstract":"Gradient-based meta-learning and hyperparameter optimization have seen significant progress recently, enabling practical end-to-end training of neural networks together with many hyperparameters. Nevertheless, existing approaches are relatively expensive as they need to compute second-order derivatives and store a longer computational graph. This cost prevents scaling them to larger network architectures. We present EvoGrad, a new approach to meta-learning that draws upon evolutionary techniques to more efficiently compute hypergradients. EvoGrad estimates hypergradient with respect to hyperparameters without calculating second-order gradients, or storing a longer computational graph, leading to significant improvements in efficiency. We evaluate EvoGrad on three substantial recent meta-learning applications, namely cross-domain few-shot learning with feature-wise transformations, noisy label learning with Meta-Weight-Net and low-resource cross-lingual learning with meta representation transformation. The results show that EvoGrad significantly improves efficiency and enables scaling meta-learning to bigger architectures such as from ResNet10 to ResNet34.","url_abs":"https://arxiv.org/abs/2106.10575v2","url_pdf":"https://arxiv.org/pdf/2106.10575v2.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":"evograd-efficient-gradient-based-meta","repo_url":"https://github.com/ondrejbohdal/evograd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-domain-few-shot","task_name":"Cross-Domain Few-Shot"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"cross-domain-few-shot-learning","task_name":"cross-domain few-shot learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.10575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.10575"}},"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":"deterministic:regex_extraction","url":"https://github.com/ondrejbohdal/evograd","reach":null}],"summary":{"ran_draft_wrong":4,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":3,"repositories":1},"community":{"samples":2,"ran":1,"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":3,"samples":[{"code_sha256_prefix":"c4806e075ebe8fb0","entry":"convert_examples_to_features","repo":"ondrejbohdal/evograd","repo_kind":"official","path":"CrossLingualLearningMetaXL/mtrain.py","file_url":"https://github.com/ondrejbohdal/evograd/blob/HEAD/CrossLingualLearningMetaXL/mtrain.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c4806e075ebe8fb0"}},{"code_sha256_prefix":"74c63bb5cff264d6","entry":"expectation","repo":"uber-research/EvoGrad","repo_kind":"community","path":"evograd/expectation.py","file_url":"https://github.com/uber-research/EvoGrad/blob/HEAD/evograd/expectation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"74c63bb5cff264d6"}},{"code_sha256_prefix":"25b7c604b7346978","entry":"extract_args_from_json","repo":"ondrejbohdal/evograd","repo_kind":"official","path":"LabelNoiseMetaWeightNet/meta-weight-net-label-noise.py","file_url":"https://github.com/ondrejbohdal/evograd/blob/HEAD/LabelNoiseMetaWeightNet/meta-weight-net-label-noise.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"25b7c604b7346978"}},{"code_sha256_prefix":"b23c45da1891b8ed","entry":"readfile","repo":"ondrejbohdal/evograd","repo_kind":"official","path":"CrossLingualLearningMetaXL/mtrain.py","file_url":"https://github.com/ondrejbohdal/evograd/blob/HEAD/CrossLingualLearningMetaXL/mtrain.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b23c45da1891b8ed"}},{"code_sha256_prefix":"f0c9a29156911331","entry":"accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f0c9a29156911331"}},{"code_sha256_prefix":"b6ff598187d9c7d8","entry":"pad","repo":"ondrejbohdal/evograd","repo_kind":"official","path":"LabelNoiseMetaWeightNet/meta-weight-net-label-noise.py","file_url":"https://github.com/ondrejbohdal/evograd/blob/HEAD/LabelNoiseMetaWeightNet/meta-weight-net-label-noise.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":"b6ff598187d9c7d8"}},{"code_sha256_prefix":"6f3c5ba1bac8315c","entry":"unsqueeze_as","repo":"uber-research/EvoGrad","repo_kind":"community","path":"evograd/expectation.py","file_url":"https://github.com/uber-research/EvoGrad/blob/HEAD/evograd/expectation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6f3c5ba1bac8315c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}