{"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/progressive-differentiable-architecture","title":"Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation","arxiv_id":"1904.12760","date":"2019-04-29","proceeding":"ICCV 2019 10","authors":["Xin Chen","Lingxi Xie","Jun Wu","Qi Tian"],"abstract":"Recently, differentiable search methods have made major progress in reducing\nthe computational costs of neural architecture search. However, these\napproaches often report lower accuracy in evaluating the searched architecture\nor transferring it to another dataset. This is arguably due to the large gap\nbetween the architecture depths in search and evaluation scenarios. In this\npaper, we present an efficient algorithm which allows the depth of searched\narchitectures to grow gradually during the training procedure. This brings two\nissues, namely, heavier computational overheads and weaker search stability,\nwhich we solve using search space approximation and regularization,\nrespectively. With a significantly reduced search time (~7 hours on a single\nGPU), our approach achieves state-of-the-art performance on both the proxy\ndataset (CIFAR10 or CIFAR100) and the target dataset (ImageNet). Code is\navailable at https://github.com/chenxin061/pdarts.","url_abs":"http://arxiv.org/abs/1904.12760v1","url_pdf":"http://arxiv.org/pdf/1904.12760v1.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":"progressive-differentiable-architecture","repo_url":"https://github.com/chenxin061/pdarts","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"progressive-differentiable-architecture","repo_url":"https://github.com/aragakiyuiii/gumbel-pdarts-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"progressive-differentiable-architecture","repo_url":"https://github.com/siddikui/ProgressiveDARTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"progressive-differentiable-architecture","repo_url":"https://github.com/mindspore-ai/models/tree/master/research/cv/PDarts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.12760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.12760"}},"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/siddikui/ProgressiveDARTS","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chenxin061/pdarts","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/PDarts","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aragakiyuiii/gumbel-pdarts-master","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":1},"by_repo_kind":{},"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":1,"samples":[{"code_sha256_prefix":"e7ef53e9c5847e3e","entry":"adjust_lr","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"e7ef53e9c5847e3e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}