{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T20:14:17Z","timestamp":1762460057691,"version":"3.37.3"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Department of Energy DoE","award":["DE-AC05-00OR22725"],"award-info":[{"award-number":["DE-AC05-00OR22725"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1841758"],"award-info":[{"award-number":["1841758"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tpds.2022.3140681","type":"journal-article","created":{"date-parts":[[2022,1,7]],"date-time":"2022-01-07T20:31:04Z","timestamp":1641587464000},"page":"1-1","source":"Crossref","is-referenced-by-count":5,"title":["Building High-throughput Neural Architecture Search Workflows via a Decoupled Fitness Prediction Engine"],"prefix":"10.1109","author":[{"given":"Ariel","family":"Keller Rorabaugh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Silvina","family":"Caino-Lores","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Travis","family":"Johnston","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michela","family":"Taufer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Efficient image dataset classification difficulty estimation for predicting deep-learning accuracy","author":"scheidegger","year":"2020","journal-title":"Comput Vis"},{"article-title":"Cinic-10 is not imagenet or cifar-10","year":"2018","author":"darlow","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-018-9339-y"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.03.035"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-017-0968-2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2018.00092"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.128"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0192-5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1515\/amcs-2017-0048"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3017100"},{"key":"ref28","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"2015","journal-title":"Proc 18th Int Conf Artifi Intell Statist"},{"key":"ref27","first-page":"1319","article-title":"Maxout networks","author":"goodfellow","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","first-page":"2004","article-title":"Improving CNN performance with min-max objective","author":"shi","year":"2016","journal-title":"Proc 25th Int Joint Conf Artif Intell"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.joule.2018.05.009"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00053"},{"key":"ref20","first-page":"1","article-title":"Evolutionary neural architecture search for image restoration","author":"van wyk","year":"2020","journal-title":"Proc Int Joint Conf Neural Netw"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.154"},{"key":"ref21","first-page":"2902","article-title":"Large-scale evolution of image classifiers","author":"real","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330648"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref26"},{"article-title":"The shape of learning curves: A review","year":"2021","author":"viering","key":"ref25"},{"key":"ref50","article-title":"Neural architecture search with reinforcement learning","author":"zoph","year":"2017","journal-title":"Proc 5th Int Conf Learn Representations"},{"year":"0","key":"ref51"},{"article-title":"Freeze-thaw bayesian optimization","year":"2014","author":"swersky","key":"ref55"},{"key":"ref54","article-title":"Accelerating neural architecture search using performance prediction","author":"baker","year":"2017","journal-title":"Proc NIPS Workshop Meta-Learn"},{"key":"ref53","article-title":"Learning curve prediction with bayesian neural networks","author":"klein","year":"2017","journal-title":"Proc 5th Int Conf Learn Representations"},{"key":"ref52","first-page":"3460","article-title":"Speeding up automatic hyperparameter optimization of deep neural networks by extrapolation of learning curves","author":"domhan","year":"2015","journal-title":"Proc 24th Int Joint Conf Artif Intell"},{"key":"ref10","first-page":"1","article-title":"Neural architecture search: A survey","volume":"20","author":"elsken","year":"2019","journal-title":"J Mach Learn Res"},{"article-title":"Neural architecture search without training","year":"0","author":"mellor","key":"ref11"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging6060041"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2916183"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2019.05.010"},{"key":"ref14","article-title":"Hierarchical representations for efficient architecture search","author":"liu","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321729"},{"key":"ref16","first-page":"19","article-title":"Progressive neural architecture search","author":"liu","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref17","first-page":"7827","article-title":"Neural architecture optimization","author":"luo","year":"2018","journal-title":"Proc 32nd Int Conf Adv Neural Inf Process Syst 31"},{"key":"ref18","first-page":"2020","article-title":"Neural architecture search with bayesian optimisation and optimal transport","author":"kandasamy","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3146347.3146355"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006467"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.gpb.2019.09.003"},{"article-title":"Efficient neural architecture search via parameter sharing","year":"2018","author":"pham","key":"ref6"},{"article-title":"Proxylessnas: Direct neural architecture search on target task and hardware","year":"2018","author":"cai","key":"ref5"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"dosovitskiy","key":"ref8"},{"article-title":"Large batch optimization for deep learning: Training bert in 76 minutes","year":"2019","author":"you","key":"ref7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2021.107780"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3146347.3146352"},{"key":"ref46","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"Proc Workshop Deep Learn Unsupervised Feature Learn"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICIIP.2017.8313740"},{"article-title":"Architecture Descriptions and High Frequency Accuracy and Loss Data of Random Neural Networks Trained on Image Datasets","year":"2021","author":"keller rorabaugh","key":"ref48"},{"key":"ref47","first-page":"3288","article-title":"Convolutional neural networks applied to house numbers digit classification","author":"sermanet","year":"2012","journal-title":"Proc 21st Int Conf Pattern Recognit"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"article-title":"Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms","year":"2017","author":"xiao","key":"ref41"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ITCE48509.2020.9047776"},{"key":"ref43","first-page":"85","article-title":"An analysis of convolutional neural network for fashion images classification (fashion-mnist)","author":"meshkini","year":"2019","journal-title":"Proc Int Conf Intell Inf Technol Ind"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/4359390\/09674227.pdf?arnumber=9674227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,26]],"date-time":"2022-05-26T15:58:51Z","timestamp":1653580731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9674227\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tpds.2022.3140681","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"type":"print","value":"1045-9219"},{"type":"electronic","value":"1558-2183"},{"type":"electronic","value":"2161-9883"}],"subject":[],"published":{"date-parts":[[2022]]}}}