{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T07:27:50Z","timestamp":1768289270123,"version":"3.49.0"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["1908762"],"award-info":[{"award-number":["1908762"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IIEEE Trans. Software Eng."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tse.2025.3550103","type":"journal-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T17:35:50Z","timestamp":1741714550000},"page":"1629-1644","source":"Crossref","is-referenced-by-count":1,"title":["Is Hyper-Parameter Optimization Different for Software Analytics?"],"prefix":"10.1109","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2069-5949","authenticated-orcid":false,"given":"Rahul","family":"Yedida","sequence":"first","affiliation":[{"name":"Department of Computer Science, North Carolina State University, Raleigh, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5040-3196","authenticated-orcid":false,"given":"Tim","family":"Menzies","sequence":"additional","affiliation":[{"name":"Department of Computer Science, North Carolina State University, Raleigh, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180197"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2945020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3073242"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/a:1022689900470"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/296"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/361002.361007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/2188385.2188395"},{"key":"ref8","first-page":"2546","article-title":"Algorithms for hyper-parameter optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Bergstra","year":"2011"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1484"},{"key":"ref10","article-title":"The promise repository of empirical software engineering data","author":"Boetticher","year":"2007"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab39d9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icsa.2018.00013"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/32.295895"},{"key":"ref16","article-title":"Flatter, faster: Scaling momentum for optimal speedup of SGD","author":"Cowsik","year":"2022"},{"key":"ref17","article-title":"Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data","author":"Dziugaite","year":"2017"},{"key":"ref18","article-title":"Hpobench: A collection of reproducible multi-fidelity benchmark problems for HPO","author":"Eggensperger","year":"2021"},{"key":"ref19","first-page":"1437","article-title":"BOHB: Robust and efficient hyperparameter optimization at scale","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Falkner","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/0962280206079046"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00700-x"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2016.04.017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47910-4_21"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3510456.3514168"},{"key":"ref26","article-title":"Computing the smoothness of GDA with respect to covariance matrix. Mathematics stack exchange","year":"2023"},{"key":"ref27","first-page":"507","article-title":"Why do tree-based models still outperform deep learning on typical tabular data?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Grinsztajn","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1414004.1414013"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICST.2009.45"},{"key":"ref30","first-page":"918","article-title":"Predictive entropy search for efficient global optimization of black-box functions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Hern\u00e1ndez-Lobato","year":"2014"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2012.6227135"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/168304.168306"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.1.1"},{"key":"ref34","article-title":"On the hyperparameter loss landscapes of machine learning algorithms","author":"Huang","year":"2023","journal-title":"OpenRev."},{"key":"ref35","article-title":"Three factors influencing minima in SGD","author":"Jastrz\u0119bski","year":"2017"},{"key":"ref36","article-title":"Fantastic generalization measures and where to find them","author":"Jiang","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008306431147"},{"key":"ref38","first-page":"16577","article-title":"When do flat minima optimizers work?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Kaddour","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510214"},{"key":"ref40","article-title":"Improving generalization performance by switching from Adam to SGD","author":"Keskar","year":"2017"},{"key":"ref41","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"Keskar","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2896825.2896836"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2965627"},{"issue":"1","key":"ref45","first-page":"6765","article-title":"Hyperband: A novel bandit-based approach to hyperparameter optimization","volume":"18","author":"Li","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref46","article-title":"What happens after SGD reaches zero loss?-A mathematical framework","volume-title":"Proc. 10th Int. Conf. Learn. Representations (ICLR)","author":"Li","year":"2022"},{"issue":"1","key":"ref47","first-page":"2475","article-title":"Smac3: A versatile Bayesian optimization package for hyperparameter optimization","volume":"23","author":"Lindauer","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref48","first-page":"3006","article-title":"Adaptive gradient methods with dynamic bound of learning rate","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Luo","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3196398.3196424"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3297001.3297023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177730491.MR0022058.Zbl0041.26103"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.1976.233837"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-07165-2_55"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-022-10276-6"},{"key":"ref55","first-page":"5947","article-title":"Exploring generalization in deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Neyshabur","year":"2017"},{"key":"ref56","first-page":"3","article-title":"Yahpo gym-an efficient multi-objective multi-fidelity benchmark for hyperparameter optimization","volume-title":"Proc. Int. Conf. Automated Mach. Learn.","author":"Pfisterer","year":"2022"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3558774"},{"key":"ref58","first-page":"1020","article-title":"Towards flatter loss surface via nonmonotonic learning rate scheduling","volume-title":"Proc. UAI","author":"Seong","year":"2018"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884857"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/BF01016429"},{"key":"ref62","first-page":"3","article-title":"Bayesian optimization is superior to random search for machine learning hyperparameter tuning: Analysis of the black-box optimization challenge 2020","volume-title":"Proc. Competition Demonstration Track","author":"Turner","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220058"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2018.2877678"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3239235.3239523"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884804"},{"issue":"3","key":"ref67","first-page":"69","article-title":"Gaussian processes for machine learning","volume":"2","author":"Williams","year":"2006","journal-title":"Int. J. Neural Syst."},{"key":"ref68","first-page":"4148","article-title":"The marginal value of adaptive gradient methods in machine learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Wilson","year":"2017"},{"key":"ref69","article-title":"The implicit regularization of dynamical stability in stochastic gradient descent","author":"Wu","year":"2023"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/2786805.2786852"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.061"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-021-09948-6"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3079841"},{"key":"ref74","article-title":"Old but gold: Reconsidering the value of feedforward learners for software analytics","author":"Yedida","year":"2021"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2023.3234206"},{"key":"ref76","article-title":"Hyper-parameter optimization: A review of algorithms and applications","author":"Yu","year":"2020"},{"key":"ref77","first-page":"21285","article-title":"Towards theoretically understanding why SGD generalizes better than Adam in deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhou","year":"2020"}],"container-title":["IEEE Transactions on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/32\/11048386\/10919477-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/32\/11048386\/10919477.pdf?arnumber=10919477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T07:08:40Z","timestamp":1750748920000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10919477\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":77,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tse.2025.3550103","relation":{},"ISSN":["0098-5589","1939-3520","2326-3881"],"issn-type":[{"value":"0098-5589","type":"print"},{"value":"1939-3520","type":"electronic"},{"value":"2326-3881","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}