{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:23:28Z","timestamp":1740101008807,"version":"3.37.3"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61831014"],"award-info":[{"award-number":["61831014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892746","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-4","source":"Crossref","is-referenced-by-count":0,"title":["DAPID: A Differential-adaptive PID Optimization Strategy for Neural Network Training"],"prefix":"10.1109","author":[{"given":"Yulin","family":"Cai","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoqian","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2963066"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102970"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"ref13","article-title":"On the variance of the adaptive learning rate and beyond","author":"liu","year":"2020","journal-title":"Proceedings of the Eighth International Conference on Learning Representations (ICLR 2020)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICIEA48937.2020.9248376"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref16","article-title":"Unveiling the power of mixup for stronger classifiers","author":"liu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref17","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref4","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.29007\/21r5"},{"journal-title":"Fixing weight decay regularization in adam","year":"2018","author":"loshchilov","key":"ref6"},{"key":"ref5","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"On the convergence of adam and beyond","author":"reddi","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref7","article-title":"Quasi-hyperbolic momentum and adam for deep learning","author":"ma","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref2","article-title":"Highly scalable deep learning training system with mixed-precision: Training imagenet in four minutes","author":"jia","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225069"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00889"},{"journal-title":"Training Deep Networks with Stochastic Gradient Normalized by Layerwise Adaptive Second Moments","year":"2019","author":"ginsburg","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892746.pdf?arnumber=9892746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:27:04Z","timestamp":1667525224000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892746\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892746","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}