{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:26:22Z","timestamp":1775143582316,"version":"3.50.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tpami.2021.3071343","type":"journal-article","created":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T20:34:21Z","timestamp":1617827661000},"page":"1-1","source":"Crossref","is-referenced-by-count":34,"title":["Sample-Efficient Neural Architecture Search by Learning Actions for Monte Carlo Tree Search"],"prefix":"10.1109","author":[{"given":"Linnan","family":"Wang","sequence":"first","affiliation":[{"name":"computer science, Brown University, 6752 Providence, Rhode Island, United States, 02912 (e-mail: wangnan318@gmail.com)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saining","family":"Xie","sequence":"additional","affiliation":[{"name":"Facebook AI Research, Menlo Park, California, United States, (e-mail: s9xie@fb.com)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Teng","family":"Li","sequence":"additional","affiliation":[{"name":"Facebook, Menlo Park, California, United States, (e-mail: tengli@fb.com)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rodrigo","family":"Fonseca","sequence":"additional","affiliation":[{"name":"Computer Science, Brown University, Providence, Rhode Island, United States, 02912-1910 (e-mail: rfonseca@cs.brown.edu)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuandong","family":"Tian","sequence":"additional","affiliation":[{"name":"Facebook AI Research, Facebook, Menlo Park, California, United States, (e-mail: yuandong.tian@gmail.com)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Neural architecture search with reinforcement learning,","author":"Zoph","year":"2016"},{"key":"ref2","article-title":"Designing neural network architectures using reinforcement learning,","author":"Baker","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i06.6554"},{"key":"ref4","article-title":"BOHB: Robust and efficient hyperparameter optimization at scale,","author":"Falkner","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref6","article-title":"Automated configuration of algorithms for solving hard computational problems,","author":"Hutter","year":"2009"},{"key":"ref7","article-title":"Hyperband: A novel bandit-based approach to hyperparameter optimization,","author":"Li","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2464576.2501592"},{"key":"ref9","first-page":"2546","article-title":"Algorithms for hyper-parameter optimization,","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bergstra"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref11","article-title":"Random search and reproducibility for neural architecture search,","author":"Li","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i06.6554"},{"key":"ref13","article-title":"ELF OpenGo: An analysis and open reimplementation of alphazero,","author":"Tian","year":"2019"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1023\/A:1013689704352","article-title":"Finite-time analysis of the multiarmed bandit problem,","volume":"47","author":"Auer","year":"2002","journal-title":"Mach. Learn."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2307\/2986138"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/203082.203089"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1198\/jcgs.2011.09058"},{"key":"ref18","first-page":"4092","article-title":"Efficient neural architecture search via parameter sharing,","author":"Pham","year":"2018","journal-title":"in Proc. Int. Conf. Mach. Learn."},{"key":"ref19","article-title":"Evaluating the search phase of neural architecture search,","author":"Sciuto","year":"2019"},{"key":"ref20","article-title":"Darts: Differentiable architecture search,","author":"Liu","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref23","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks,","author":"Tan","year":"2019"},{"key":"ref24","article-title":"Once-for-all: Train one network and specialize it for efficient deployment,","author":"Cai","year":"2019"},{"issue":"3","key":"ref25","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1080\/00031305.1991.10475815","article-title":"Letters to the editor,","volume":"45","author":"Mallows","year":"1991","journal-title":"Amer. Statistician"},{"key":"ref26","article-title":"NAS-Bench-101: Towards reproducible neural architecture search,","author":"Ying","year":"2019"},{"key":"ref27","first-page":"2951","article-title":"Practical Bayesian optimization of machine learning algorithms,","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Snoek"},{"key":"ref28","first-page":"1005","article-title":"Bayesian multi- scale optimistic optimization,","volume-title":"in Proc. Int. Conf. Artif. Intell. Stat.","author":"Wang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref30","first-page":"7816","article-title":"Neural architecture optimization,","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo"},{"key":"ref31","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism,","author":"Huang","year":"2018"},{"key":"ref32","article-title":"BayesNAS: A Bayesian approach for neural architecture search,","author":"Zhou","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00138"},{"key":"ref34","article-title":"PC-DARTS: Partial channel connections for memory-efficient architecture search,","author":"Xu","year":"2019"},{"key":"ref35","first-page":"3822","article-title":"Breaking the curse of space explosion: Towards efficient nas with curriculum search,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_28"},{"key":"ref37","article-title":"Adaptive stochastic natural gradient method for one-shot neural architecture search,","author":"Akimoto","year":"2019"},{"key":"ref38","first-page":"1977","article-title":"XNAS: Neural architecture search with expert advice,","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nayman"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00137"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01298"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_41"},{"key":"ref44","article-title":"FBNetV3: Joint architecture-recipe search using neural acquisition function,","author":"Dai","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899x\/750\/1\/012223"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25566-3_40"},{"issue":"4","key":"ref47","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1023\/A:1012771025575","article-title":"A taxonomy of global optimization methods based on response surfaces,","volume":"21","author":"Jones","year":"2001","journal-title":"J. Glob. Optim."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s10898-008-9354-2"},{"key":"ref49","first-page":"1778","article-title":"Bayesian optimization in high dimensions via random embeddings,","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Wang"},{"key":"ref50","first-page":"937","article-title":"Bayesian optimization with inequality constraints,","volume-title":"Proc. Int. Conf. Int. Conf. Mach. Learn.","author":"Gardner"},{"key":"ref51","article-title":"Multi-objective neural architecture search via predictive network performance optimization,","author":"Shi","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6614991"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1561\/2200000038"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v22i1.13507"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v21i1.13484"},{"key":"ref57","article-title":"Learning search space partition for black-box optimization using monte carlo tree search,","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref58","article-title":"Solving black-box optimization challenge via learning search space partition for local Bayesian optimization,","author":"Sazanovich","year":"2020"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09397771.pdf?arnumber=9397771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:07:53Z","timestamp":1704841673000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9397771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3071343","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}