{"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/unifying-and-boosting-gradient-based-training","title":"Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search","arxiv_id":"2201.09785","date":"2022-01-24","proceeding":null,"authors":["Yao Shu","Zhongxiang Dai","Zhaoxuan Wu","Bryan Kian Hsiang Low"],"abstract":"Neural architecture search (NAS) has gained immense popularity owing to its ability to automate neural architecture design. A number of training-free metrics are recently proposed to realize NAS without training, hence making NAS more scalable. Despite their competitive empirical performances, a unified theoretical understanding of these training-free metrics is lacking. As a consequence, (a) the relationships among these metrics are unclear, (b) there is no theoretical interpretation for their empirical performances, and (c) there may exist untapped potential in existing training-free NAS, which probably can be unveiled through a unified theoretical understanding. To this end, this paper presents a unified theoretical analysis of gradient-based training-free NAS, which allows us to (a) theoretically study their relationships, (b) theoretically guarantee their generalization performances, and (c) exploit our unified theoretical understanding to develop a novel framework named hybrid NAS (HNAS) which consistently boosts training-free NAS in a principled way. Remarkably, HNAS can enjoy the advantages of both training-free (i.e., the superior search efficiency) and training-based (i.e., the remarkable search effectiveness) NAS, which we have demonstrated through extensive experiments.","url_abs":"https://arxiv.org/abs/2201.09785v2","url_pdf":"https://arxiv.org/pdf/2201.09785v2.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":"unifying-and-boosting-gradient-based-training","repo_url":"https://github.com/shuyao95/HNAS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2201.09785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.09785"}},"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/shuyao95/HNAS","reach":null}],"summary":{"ran":2,"ran_fixture":1,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":4,"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":7,"samples":[{"code_sha256_prefix":"8263d673163736be","entry":"AvgrageMeter","repo":"shuyao95/HNAS","repo_kind":"official","path":"darts_space/search.py","file_url":"https://github.com/shuyao95/HNAS/blob/HEAD/darts_space/search.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8263d673163736be"}},{"code_sha256_prefix":"7314f4a68ed86e01","entry":"CrossEntropyLabelSmooth","repo":"shuyao95/HNAS","repo_kind":"official","path":"darts_space/search.py","file_url":"https://github.com/shuyao95/HNAS/blob/HEAD/darts_space/search.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7314f4a68ed86e01"}},{"code_sha256_prefix":"eab4f74c38cc3c8f","entry":"accuracy","repo":"shuyao95/HNAS","repo_kind":"official","path":"darts_space/search.py","file_url":"https://github.com/shuyao95/HNAS/blob/HEAD/darts_space/search.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eab4f74c38cc3c8f"}},{"code_sha256_prefix":"befd08c37da92424","entry":"score_arch","repo":"shuyao95/HNAS","repo_kind":"official","path":"darts_space/search.py","file_url":"https://github.com/shuyao95/HNAS/blob/HEAD/darts_space/search.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"befd08c37da92424"}},{"code_sha256_prefix":"cb2ba06748c4b4e6","entry":"infer","repo":"shuyao95/HNAS","repo_kind":"official","path":"darts_space/search.py","file_url":"https://github.com/shuyao95/HNAS/blob/HEAD/darts_space/search.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb2ba06748c4b4e6"}},{"code_sha256_prefix":"6cf5b3cb27cb5cd4","entry":"search","repo":"shuyao95/HNAS","repo_kind":"official","path":"darts_space/search.py","file_url":"https://github.com/shuyao95/HNAS/blob/HEAD/darts_space/search.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6cf5b3cb27cb5cd4"}},{"code_sha256_prefix":"41cb77ab2448be4f","entry":"train","repo":"shuyao95/HNAS","repo_kind":"official","path":"darts_space/search.py","file_url":"https://github.com/shuyao95/HNAS/blob/HEAD/darts_space/search.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"41cb77ab2448be4f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}