{"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/efficient-neural-architecture-search-via","title":"Efficient Neural Architecture Search via Parameters Sharing","arxiv_id":null,"date":"2018-07-01","proceeding":"ICML 2018 7","authors":["Hieu Pham","Melody Guan","Barret Zoph","Quoc Le","Jeff Dean"],"abstract":"\n    We propose Efficient Neural Architecture Search (ENAS), a fast and inexpensive approach for automatic model design. ENAS constructs a large computational graph, where each subgraph represents a neural network architecture, hence forcing all architectures to share their parameters. A controller is trained with policy gradient to search for a subgraph that maximizes the expected reward on a validation set. Meanwhile a model corresponding to the selected subgraph is trained to minimize a canonical cross entropy loss. Sharing parameters among child models allows ENAS to deliver strong empirical performances, whilst using much fewer GPU-hours than existing automatic model design approaches, and notably, 1000x less expensive than standard Neural Architecture Search. On Penn Treebank, ENAS discovers a novel architecture that achieves a test perplexity of 56.3, on par with the existing state-of-the-art among all methods without post-training processing. On CIFAR-10, ENAS finds a novel architecture that achieves 2.89% test error, which is on par with the 2.65% test error of NASNet (Zoph et al., 2018).\n  ","url_abs":"https://icml.cc/Conferences/2018/Schedule?showEvent=2247","url_pdf":"http://proceedings.mlr.press/v80/pham18a/pham18a.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":[],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"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"}],"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":"ENAS","rank_in_archive_order":35,"of":37,"metrics":{"Accuracy (Test)":"54.3","Accuracy (Val)":"39.77","Search time (s)":"13315"},"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":"ENAS","rank_in_archive_order":36,"of":40,"metrics":{"Accuracy (Test)":"15.61","Accuracy (Val)":"15.03","Search time (s)":"13315"},"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":"ENAS","rank_in_archive_order":43,"of":49,"metrics":{"Accuracy (Test)":"16.43","Search time (s)":"13315"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}