{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T05:30:28Z","timestamp":1782970228672,"version":"3.54.5"},"reference-count":74,"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"}],"funder":[{"name":"National Key RD Program","award":["2018AAA0102201"],"award-info":[{"award-number":["2018AAA0102201"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11971373"],"award-info":[{"award-number":["11971373"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12026605"],"award-info":[{"award-number":["12026605"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1811461"],"award-info":[{"award-number":["U1811461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20B2075"],"award-info":[{"award-number":["U20B2075"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tpami.2021.3061581","type":"journal-article","created":{"date-parts":[[2021,2,23]],"date-time":"2021-02-23T21:18:02Z","timestamp":1614115082000},"page":"1-1","source":"Crossref","is-referenced-by-count":9,"title":["Variational HyperAdam: A Meta-learning Approach to Network Training"],"prefix":"10.1109","author":[{"given":"Shipeng","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongben","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref2","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref3","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Goodfellow"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","first-page":"10","article-title":"Deep ADMM-Net for compressive sensing MRI","volume-title":"Proc. Advances. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858759"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11284"},{"key":"ref8","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lillicrap"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/S1052623495294797"},{"issue":"2","key":"ref11","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"Tieleman","year":"2012","journal-title":"COURSERA: Neural Netw. Mach. Learn."},{"key":"ref12","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref13","article-title":"Adadelta: An adaptive learning rate method","author":"Zeiler","year":"2012"},{"key":"ref14","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref15","article-title":"On the convergence of adam and beyond","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Reddi"},{"key":"ref16","article-title":"Adaptive gradient methods with dynamic bound of learning rate","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Luo"},{"key":"ref17","article-title":"AdaShift: Decorrelation and convergence of adaptive learning rate methods","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969154"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.1.131"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44668-0_13"},{"key":"ref21","first-page":"3981","article-title":"Learning to learn by gradient descent by gradient descent","volume-title":"Proc. Advances. Neural Inf. Process. Syst.","author":"Andrychowicz"},{"key":"ref22","first-page":"2247","article-title":"Learning gradient descent: Better generalization and longer horizons","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lv"},{"key":"ref23","first-page":"3751","article-title":"Learned optimizers that scale and generalize","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wichrowska"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015297"},{"key":"ref25","article-title":"Meta-Learning for semi-supervised few-shot classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren"},{"key":"ref26","first-page":"357","article-title":"One-Shot visual imitation learning via meta-learning","volume-title":"Proc. Conf. Robot Learn.","author":"Finn"},{"key":"ref27","first-page":"4077","article-title":"Prototypical networks for few-shot learning","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Snell"},{"key":"ref28","first-page":"1842","article-title":"Meta-Learning with memory-augmented neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Santoro"},{"key":"ref29","first-page":"244","article-title":"Learning from small sample sets by combining unsupervised meta-training with CNNs","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref30","first-page":"7029","article-title":"Learning to model the tail","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.14711\/thesis-991012636368103412"},{"key":"ref32","article-title":"Meta-Learning with latent embedding optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rusu"},{"key":"ref33","first-page":"998","article-title":"MetaReg: Towards domain generalization using meta-regularization","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Balaji"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"ref35","first-page":"205","article-title":"Meta-Learning by adjusting priors based on extended PAC-Bayes theory","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amit"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273558"},{"key":"ref37","first-page":"6467","article-title":"Learning to teach with dynamic loss functions","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref38","first-page":"1126","article-title":"Model-Agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1992.287172"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2001.938471"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref42","first-page":"748","article-title":"Learning to learn without gradient descent by gradient descent","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref43","first-page":"459","article-title":"Neural optimizer search with reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bello"},{"key":"ref44","article-title":"Learning to infer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Marino"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11523"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2883941"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80023-1"},{"issue":"1","key":"ref48","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref49","first-page":"351","article-title":"Dropout training as adaptive regularization","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Wager"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5555\/2986459.2986721"},{"key":"ref51","first-page":"1613","article-title":"Weight uncertainty in neural network","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Blundell"},{"key":"ref52","first-page":"5847","article-title":"Noisy natural gradient as variational inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref53","first-page":"681","article-title":"Bayesian learning via stochastic gradient langevin dynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Welling"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10200"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.1.108"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/21.155944"},{"key":"ref57","article-title":"Adding noise to the input of a model trained with a regularized objective","author":"Rifai","year":"2011"},{"key":"ref58","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1100.003.0014"},{"key":"ref60","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Clevert"},{"issue":"2","key":"ref61","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1023\/A:1022859003006","article-title":"Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy","volume":"51","author":"Kuncheva","year":"2003","journal-title":"Mach. Learn."},{"key":"ref62","first-page":"2352","article-title":"Variational autoencoder for deep learning of images, labels and captions","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Pu"},{"key":"ref63","first-page":"7795","article-title":"Constrained graph variational autoencoders for molecule design","volume-title":"Proc. Advances. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref64","first-page":"52","article-title":"IntroVAE: Introspective variational autoencoders for photographic image synthesis","volume-title":"Proc. Advances. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref65","article-title":"beta-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Higgins"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref67","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref68","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref69","article-title":"The UCR time series classification archive","author":"Dau","year":"2018"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1017\/9781108924238.008"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s13398-014-0173-7.2"},{"key":"ref72","article-title":"Towards understanding regularization in batch normalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Luo"},{"key":"ref73","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wan"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-45528-0"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09361276.pdf?arnumber=9361276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:43:11Z","timestamp":1704840191000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9361276\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3061581","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]]}}}