{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:40:09Z","timestamp":1755913209583,"version":"3.44.0"},"reference-count":79,"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":"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":[{"name":"NSF","award":["IIS2405974","IIS2339216"],"award-info":[{"award-number":["IIS2405974","IIS2339216"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tai.2025.3534151","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T14:10:56Z","timestamp":1737987056000},"page":"1651-1663","source":"Crossref","is-referenced-by-count":0,"title":["Learning From Mistakes: A Multilevel Optimization Framework"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1877-1658","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California, San Diego, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3511-8183","authenticated-orcid":false,"given":"Bhanu","family":"Garg","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California, San Diego, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5527-5461","authenticated-orcid":false,"given":"Pradyumna","family":"Sridhara","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California, San Diego, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0684-1743","authenticated-orcid":false,"given":"Ramtin","family":"Hosseini","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California, San Diego, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0521-174X","authenticated-orcid":false,"given":"Pengtao","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California, San Diego, CA, USA"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1007\/978-3-030-52119-6_20"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TPAMI.2021.3132674"},{"year":"2016","author":"Zoph","article-title":"Neural architecture search with reinforcement learning","key":"ref3"},{"key":"ref4","first-page":"5008","article-title":"Hierarchical representations for efficient architecture search","volume":"7","author":"Liu","year":"2018","journal-title":"Proc. Int. Conf. Learn. Represent."},{"key":"ref5","article-title":"Darts: Differentiable architecture search","author":"Liu","year":"2018","journal-title":"Proc. Int. Conf. Learn. Represent."},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1613\/jair.953"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1145\/1015330.1015425"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.5555\/1642194.1642224"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1007\/978-3-030-05318-5_3"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.3390\/app10082749"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1093\/bib\/bbx044"},{"key":"ref12","first-page":"1919","article-title":"Meta-weight-net: Learning an explicit mapping for sample weighting","author":"Shu","year":"2019","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1609\/aaai.v34i04.6024"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1016\/j.patcog.2007.04.009"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref16","first-page":"1002","article-title":"Active bias: Training more accurate neural networks by emphasizing high variance samples","volume":"30","author":"Chang","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref17","first-page":"1189","article-title":"Self-paced learning for latent variable models","volume":"23","author":"Kumar","year":"2010","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref18","first-page":"2304","article-title":"Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels","author":"Jiang","year":"2018","journal-title":"Proc. Int. Conf. Mach. Learn."},{"key":"ref19","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","author":"Zhang","year":"2018","journal-title":"Proc. 32nd Conf. Neural Inf. Process. Syst. (NeurIPS)"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1609\/aaai.v29i1.9354"},{"key":"ref21","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"Finn","year":"2017","journal-title":"Proc. Int. Conf. Mach. Learn."},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1007\/978-3-030-58555-6_8"},{"key":"ref23","first-page":"1568","article-title":"Bilevel programming for hyperparameter optimization and meta-learning","author":"Franceschi","year":"2018","journal-title":"Proc. Int. Conf. Mach. Learn."},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1609\/aaai.v34i07.6876"},{"key":"ref25","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","author":"Pham","year":"2018","journal-title":"Proc. Int. Conf. Mach. Learn."},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/CVPR.2018.00907"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref28","article-title":"Proxylessnas: Direct neural architecture search on target task and hardware","author":"Cai","year":"2018","journal-title":"Proc. Int. Conf. Learn. Represent."},{"key":"ref29","article-title":"SNAS: stochastic neural architecture search","author":"Xie","year":"2018","journal-title":"Proc. Int. Conf. Learn. Represent."},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/ICCV.2019.00138"},{"key":"ref31","article-title":"PC-DARTS: Partial channel connections for memory-efficient architecture search","author":"Xu","year":"2019","journal-title":"Proc. Int. Conf. Learn. Represent."},{"year":"2019","author":"Liang","article-title":"Darts+: Improved differentiable architecture search with early stopping","key":"ref32"},{"key":"ref33","article-title":"Darts-: Robustly stepping out of performance collapse without indicators","author":"Chu","year":"2020","journal-title":"Proc. Int. Conf. Learn. Represent."},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/TNNLS.2017.2732482"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1006\/jcss.1997.1504"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/ICCV.2011.6126229"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/5254.708428"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1162\/neco.1997.9.8.1735"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1145\/1553374.1553380"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.18653\/v1\/D15-1166"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1109\/CVPR.2016.90"},{"year":"2020","author":"Xie","article-title":"Skillearn: Machine learning inspired by humans\u2019 learning skills","key":"ref42"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1109\/CVPR.2017.243"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1007\/978-3-030-01246-5_2"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1109\/CVPR.2019.00186"},{"key":"ref46","article-title":"Understanding and robustifying differentiable architecture search","author":"Zela","year":"2019","journal-title":"Int. Conf. Learn. Represent."},{"doi-asserted-by":"publisher","key":"ref47","DOI":"10.24963\/ijcai.2020\/322"},{"year":"2018","author":"Liu","article-title":"Hierarchical representations for efficient architecture search","key":"ref48"},{"key":"ref49","first-page":"9206","article-title":"Generative teaching networks: Accelerating neural architecture search by learning to generate synthetic training data","author":"Such","year":"2020","journal-title":"Proc. Int. Conf. Mach. Learn."},{"key":"ref50","first-page":"7603","article-title":"Bayesnas: A Bayesian approach for neural architecture search","author":"Zhou","year":"2019","journal-title":"Int. Conf. Mach. Learn."},{"doi-asserted-by":"publisher","key":"ref51","DOI":"10.24963\/ijcai.2020\/424"},{"year":"2020","author":"Chu","article-title":"Noisy differentiable architecture search","key":"ref52"},{"key":"ref53","first-page":"493","article-title":"Asap: Architecture search, anneal and prune","author":"Noy","year":"2020","journal-title":"Proc. Int. Conf. Artif. Intell. Stat."},{"key":"ref54","first-page":"1554","article-title":"Stabilizing differentiable architecture search via perturbation-based regularization","author":"Chen","year":"2020","journal-title":"Proc. Int. Conf. Mach. Learn."},{"key":"ref55","article-title":"DrNAS: Dirichlet neural architecture search","author":"Chen","year":"2020","journal-title":"Proc. Int. Conf. Learn. Represent."},{"doi-asserted-by":"publisher","key":"ref56","DOI":"10.4324\/9781410605337-29"},{"year":"2017","author":"Howard","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","key":"ref57"},{"doi-asserted-by":"publisher","key":"ref58","DOI":"10.1109\/CVPR.2018.00716"},{"doi-asserted-by":"publisher","key":"ref59","DOI":"10.1007\/978-3-030-01264-9_8"},{"doi-asserted-by":"publisher","key":"ref60","DOI":"10.1109\/CVPR.2019.00293"},{"year":"2019","author":"Casale","article-title":"Probabilistic neural architecture search","key":"ref61"},{"doi-asserted-by":"publisher","key":"ref62","DOI":"10.1109\/CVPR42600.2020.01210"},{"doi-asserted-by":"publisher","key":"ref63","DOI":"10.1007\/978-3-030-58555-6_28"},{"key":"ref64","first-page":"60","article-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky","year":"2009","journal-title":"Citeseer"},{"doi-asserted-by":"publisher","key":"ref65","DOI":"10.1109\/CVPR.2009.5206848"},{"doi-asserted-by":"publisher","key":"ref66","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref67","first-page":"4334","article-title":"Learning to reweight examples for robust deep learning","author":"Ren","year":"2018","journal-title":"Int. Conf. Mach. Learn."},{"key":"ref68","article-title":"Training deep neural networks on noisy labels with bootstrapping","author":"Reed","year":"2015","journal-title":"Proc. ICLR (Workshop)"},{"doi-asserted-by":"publisher","key":"ref69","DOI":"10.4135\/9781071810118"},{"key":"ref70","first-page":"3355","article-title":"Dimensionality-driven learning with noisy labels","author":"Ma","year":"2018","journal-title":"Proc. Int. Conf. Mach. Learn."},{"key":"ref71","article-title":"Using trusted data to train deep networks on labels corrupted by severe noise","volume":"31","author":"Hendrycks","year":"2018","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"doi-asserted-by":"publisher","key":"ref72","DOI":"10.1145\/3446776"},{"key":"ref73","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009","journal-title":"Citeseer"},{"doi-asserted-by":"publisher","key":"ref74","DOI":"10.5244\/C.30.87"},{"key":"ref75","first-page":"5907","article-title":"Selfie: Refurbishing unclean samples for robust deep learning","author":"Song","year":"2019","journal-title":"Proc. Int. Conf. Mach. Learn."},{"year":"2014","author":"Simonyan","article-title":"Very deep convolutional networks for large-scale image recognition","key":"ref76"},{"doi-asserted-by":"publisher","key":"ref77","DOI":"10.1109\/CVPRW53098.2021.00302"},{"key":"ref78","article-title":"Learning with feature-dependent label noise: A progressive approach","author":"Zhang","year":"2020","journal-title":"Int. Conf. Learn. Represent."},{"doi-asserted-by":"publisher","key":"ref79","DOI":"10.1038\/s41598-023-44791-3"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/11021002\/10855680.pdf?arnumber=10855680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:48Z","timestamp":1755911388000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10855680\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":79,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tai.2025.3534151","relation":{},"ISSN":["2691-4581"],"issn-type":[{"type":"electronic","value":"2691-4581"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}