{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/searching-for-a-robust-neural-architecture-in-1","title":"Searching for A Robust Neural Architecture in Four GPU Hours","arxiv_id":"1910.04465","date":"2019-10-10","proceeding":"CVPR 2019 6","authors":["Xuanyi Dong","Yi Yang"],"abstract":"Conventional neural architecture search (NAS) approaches are based on reinforcement learning or evolutionary strategy, which take more than 3000 GPU hours to find a good model on CIFAR-10. We propose an efficient NAS approach learning to search by gradient descent. Our approach represents the search space as a directed acyclic graph (DAG). This DAG contains billions of sub-graphs, each of which indicates a kind of neural architecture. To avoid traversing all the possibilities of the sub-graphs, we develop a differentiable sampler over the DAG. This sampler is learnable and optimized by the validation loss after training the sampled architecture. In this way, our approach can be trained in an end-to-end fashion by gradient descent, named Gradient-based search using Differentiable Architecture Sampler (GDAS). In experiments, we can finish one searching procedure in four GPU hours on CIFAR-10, and the discovered model obtains a test error of 2.82\\% with only 2.5M parameters, which is on par with the state-of-the-art. Code is publicly available on GitHub: https://github.com/D-X-Y/NAS-Projects.","url_abs":"https://arxiv.org/abs/1910.04465v2","url_pdf":"https://arxiv.org/pdf/1910.04465v2.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":"searching-for-a-robust-neural-architecture-in-1","repo_url":"https://github.com/D-X-Y/NAS-Projects","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"searching-for-a-robust-neural-architecture-in-1","repo_url":"https://github.com/D-X-Y/AutoDL-Projects","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"searching-for-a-robust-neural-architecture-in-1","repo_url":"https://github.com/D-X-Y/GDAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"searching-for-a-robust-neural-architecture-in-1","repo_url":"https://github.com/epfl-ml-reproducers/subspace-attack-reproduction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"searching-for-a-robust-neural-architecture-in-1","repo_url":"https://github.com/rwbfd/OpenCompetitionV2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"searching-for-a-robust-neural-architecture-in-1","repo_url":"https://github.com/xxlya/COS598D_Assignment1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/neural-architecture-search-on-cifar-10","task":"Neural Architecture Search","dataset":"CIFAR-10","model":"GDAS (FRC)","rank_in_archive_order":18,"of":41,"metrics":{"Search Time (GPU days)":"0.17","Top-1 Error Rate":"2.5%"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-cifar-10","task":"Neural Architecture Search","dataset":"CIFAR-10","model":"GDAS","rank_in_archive_order":40,"of":41,"metrics":{"Search Time (GPU days)":"0.21","Top-1 Error Rate":"3.4%"},"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":"GDAS","rank_in_archive_order":22,"of":37,"metrics":{"Accuracy (Test)":"93.61","Accuracy (Val)":"89.89","Search time (s)":"28926"},"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":"GDAS","rank_in_archive_order":26,"of":40,"metrics":{"Accuracy (Test)":"70.70","Accuracy (Val)":"71.34","Search time (s)":"28926"},"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":"GDAS","rank_in_archive_order":36,"of":49,"metrics":{"Accuracy (Test)":"41.71","Search time (s)":"28926"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1910.04465","atlas_url":"https://app.syntology.ai/?focus=1910.04465","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1910.04465"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1910.04465\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1910.04465"},"call":"get_concepts_for_paper(arxiv_id=\"1910.04465\")"}],"by_repo":[{"repo":"D-X-Y/NAS-Projects","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2001.00326"],"harvested_for_calls":[{"arxiv_id":"2001.00326","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2001.00326"},"call":"get_harvested_code_for_paper(arxiv_id=\"2001.00326\")"}]},{"repo":"D-X-Y/AutoDL-Projects","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2107.00860"],"harvested_for_calls":[{"arxiv_id":"2107.00860","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2107.00860"},"call":"get_harvested_code_for_paper(arxiv_id=\"2107.00860\")"}]},{"repo":"D-X-Y/GDAS","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1910.05733"],"harvested_for_calls":[{"arxiv_id":"1910.05733","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1910.05733"},"call":"get_harvested_code_for_paper(arxiv_id=\"1910.05733\")"}]},{"repo":"epfl-ml-reproducers/subspace-attack-reproduction","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1605.07146"],"harvested_for_calls":[{"arxiv_id":"1605.07146","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1605.07146"},"call":"get_harvested_code_for_paper(arxiv_id=\"1605.07146\")"}]},{"repo":"rwbfd/OpenCompetitionV2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"xxlya/COS598D_Assignment1","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"8ef37f58e303e615f26b37ac9927d1fec8bb7e2968435a2800cb6608e52c22f8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}