{"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/epe-nas-efficient-performance-estimation","title":"EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search","arxiv_id":"2102.08099","date":"2021-02-16","proceeding":null,"authors":["Vasco Lopes","Saeid Alirezazadeh","Luís A. Alexandre"],"abstract":"Neural Architecture Search (NAS) has shown excellent results in designing architectures for computer vision problems. NAS alleviates the need for human-defined settings by automating architecture design and engineering. However, NAS methods tend to be slow, as they require large amounts of GPU computation. This bottleneck is mainly due to the performance estimation strategy, which requires the evaluation of the generated architectures, mainly by training them, to update the sampler method. In this paper, we propose EPE-NAS, an efficient performance estimation strategy, that mitigates the problem of evaluating networks, by scoring untrained networks and creating a correlation with their trained performance. We perform this process by looking at intra and inter-class correlations of an untrained network. We show that EPE-NAS can produce a robust correlation and that by incorporating it into a simple random sampling strategy, we are able to search for competitive networks, without requiring any training, in a matter of seconds using a single GPU. Moreover, EPE-NAS is agnostic to the search method, since it focuses on the evaluation of untrained networks, making it easy to integrate into almost any NAS method.","url_abs":"https://arxiv.org/abs/2102.08099v1","url_pdf":"https://arxiv.org/pdf/2102.08099v1.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":"epe-nas-efficient-performance-estimation","repo_url":"https://github.com/VascoLopes/EPENAS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"epe-nas-efficient-performance-estimation","repo_url":"https://github.com/VascoLopes/EPE-NAS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201-1","task":"Neural Architecture Search","dataset":"NAS-Bench-201, CIFAR-10","model":"EPE-NAS (N=10)","rank_in_archive_order":28,"of":37,"metrics":{"Accuracy (Test)":"92.63","Accuracy (Val)":"89.90","Search time (s)":"2.3"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201-1","task":"Neural Architecture Search","dataset":"NAS-Bench-201, CIFAR-10","model":"EPE-NAS (N=500)","rank_in_archive_order":29,"of":37,"metrics":{"Accuracy (Test)":"92.27","Accuracy (Val)":"88.17","Search time (s)":"105.8"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201-1","task":"Neural Architecture Search","dataset":"NAS-Bench-201, CIFAR-10","model":"EPE-NAS (N=100)","rank_in_archive_order":30,"of":37,"metrics":{"Accuracy (Test)":"91.59","Accuracy (Val)":"88.74","Search time (s)":"20.5"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201-1","task":"Neural Architecture Search","dataset":"NAS-Bench-201, CIFAR-10","model":"EPE-NAS (N=1000)","rank_in_archive_order":31,"of":37,"metrics":{"Accuracy (Test)":"91.31","Accuracy (Val)":"87.87","Search time (s)":"206.2"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201-2","task":"Neural Architecture Search","dataset":"NAS-Bench-201, CIFAR-100","model":"EPE-NAS (N=10)","rank_in_archive_order":27,"of":40,"metrics":{"Accuracy (Test)":"70.10","Accuracy (Val)":"69.78","Search time (s)":"2.3"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201-2","task":"Neural Architecture Search","dataset":"NAS-Bench-201, CIFAR-100","model":"EPE-NAS (N=1000)","rank_in_archive_order":28,"of":40,"metrics":{"Accuracy (Test)":"69.58","Accuracy (Val)":"69.44","Search time (s)":"206.2"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201-2","task":"Neural Architecture Search","dataset":"NAS-Bench-201, CIFAR-100","model":"EPE-NAS (N=500)","rank_in_archive_order":31,"of":40,"metrics":{"Accuracy (Test)":"69.33","Accuracy (Val)":"69.23","Search time (s)":"105.8"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201-2","task":"Neural Architecture Search","dataset":"NAS-Bench-201, CIFAR-100","model":"EPE-NAS (N=100)","rank_in_archive_order":32,"of":40,"metrics":{"Accuracy (Test)":"67.19","Accuracy (Val)":"67.28","Search time (s)":"20.5"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201","task":"Neural Architecture Search","dataset":"NAS-Bench-201, ImageNet-16-120","model":"EPE-NAS (N=500)","rank_in_archive_order":33,"of":49,"metrics":{"Accuracy (Test)":"42.05","Search time (s)":"105.8"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201","task":"Neural Architecture Search","dataset":"NAS-Bench-201, ImageNet-16-120","model":"EPE-NAS (N=10)","rank_in_archive_order":34,"of":49,"metrics":{"Accuracy (Test)":"41.92","Search time (s)":"2.3"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201","task":"Neural Architecture Search","dataset":"NAS-Bench-201, ImageNet-16-120","model":"EPE-NAS (N=1000)","rank_in_archive_order":35,"of":49,"metrics":{"Accuracy (Test)":"41.84","Search time (s)":"206.2"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201","task":"Neural Architecture Search","dataset":"NAS-Bench-201, ImageNet-16-120","model":"EPE-NAS (N=100)","rank_in_archive_order":38,"of":49,"metrics":{"Accuracy (Test)":"38.80","Search time (s)":"20.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2102.08099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.08099"}},"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/VascoLopes/EPE-NAS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/VascoLopes/EPENAS","reach":{"status":"unanswered"}}],"summary":{"ran_honours":1,"ran_fixture":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"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":"5819779af11c2caf","entry":"eval_score","repo":"VascoLopes/EPE-NAS","repo_kind":"official","path":"search.py","file_url":"https://github.com/VascoLopes/EPE-NAS/blob/HEAD/search.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5819779af11c2caf"}},{"code_sha256_prefix":"78fdf3831a585295","entry":"eval_score_perclass","repo":"VascoLopes/EPE-NAS","repo_kind":"official","path":"search.py","file_url":"https://github.com/VascoLopes/EPE-NAS/blob/HEAD/search.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"78fdf3831a585295"}},{"code_sha256_prefix":"271a1e01e67260a2","entry":"get_batch_jacobian","repo":"VascoLopes/EPE-NAS","repo_kind":"official","path":"search.py","file_url":"https://github.com/VascoLopes/EPE-NAS/blob/HEAD/search.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"271a1e01e67260a2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}