{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T11:12:16Z","timestamp":1730200336242,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,12,10]]},"DOI":"10.1109\/bigdata50022.2020.9378007","type":"proceedings-article","created":{"date-parts":[[2021,3,19]],"date-time":"2021-03-19T21:10:21Z","timestamp":1616188221000},"page":"5269-5275","source":"Crossref","is-referenced-by-count":2,"title":["Optimizing Stochastic Gradient Descent Using the Angle Between Gradients"],"prefix":"10.1109","author":[{"given":"Chongya","family":"Song","sequence":"first","affiliation":[]},{"given":"Alexander","family":"Pons","sequence":"additional","affiliation":[]},{"given":"Kang","family":"Yen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Incorporating Nesterov Momentum into Adam","author":"dozat","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref11","article-title":"On the convergence of Adam and beyond","author":"reddi","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"article-title":"An overview of gradient descent optimization algorithms","year":"2017","author":"ruder","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"article-title":"Google's neural machine translation system: bridging the gap between human and machine translation","year":"2016","author":"wu","key":"ref14"},{"article-title":"On empirical comparisons of optimizers for deep learning","year":"2020","author":"choi","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICACSIS.2017.8355063"},{"journal-title":"Keras (2 4 0)","year":"0","key":"ref17"},{"journal-title":"Keras (2 4 0)","year":"0","key":"ref18"},{"article-title":"The marginal value of adaptive gradient methods in machine learning","year":"2018","author":"wilson","key":"ref19"},{"key":"ref4","first-page":"543","article-title":"A method for unconstrained convex minimization problem with the rate of convergence o(1\/k2)","volume":"269","author":"nesterov","year":"1983","journal-title":"Dokl Akad Nauk SSSR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(64)90137-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966082"},{"key":"ref5","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","article-title":"Adam: a method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations"},{"article-title":"ADADELTA: An adaptive learning rate method","year":"2012","author":"zeiler","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2912200"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IDAP.2017.8090299"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CTEMS.2018.8769211"},{"key":"ref20","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","article-title":"The step decay schedule: a near optimal, geometrically decaying learning rate procedure for least squares","author":"ge","year":"2019","journal-title":"Conference on Neural Information Processing Systems (NeurIPS)"},{"key":"ref21","article-title":"A simple weight decay can improve generalization","author":"krogh","year":"1991","journal-title":"Conference on Neural Information Processing Systems"}],"event":{"name":"2020 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2020,12,10]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2020,12,13]]}},"container-title":["2020 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9377717\/9377728\/09378007.pdf?arnumber=9378007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T15:52:42Z","timestamp":1656345162000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9378007\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,10]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/bigdata50022.2020.9378007","relation":{},"subject":[],"published":{"date-parts":[[2020,12,10]]}}}