{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:22:31Z","timestamp":1776885751976,"version":"3.51.2"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T00:00:00Z","timestamp":1605571200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T00:00:00Z","timestamp":1605571200000},"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":[[2020,11,17]]},"DOI":"10.1109\/iit50501.2020.9299013","type":"proceedings-article","created":{"date-parts":[[2020,12,25]],"date-time":"2020-12-25T22:07:25Z","timestamp":1608934045000},"page":"209-214","source":"Crossref","is-referenced-by-count":8,"title":["AdaDiffGrad: An Adaptive Batch Size Implementation Technique for DiffGrad Optimization Method"],"prefix":"10.1109","author":[{"given":"Wajid","family":"Khan","sequence":"first","affiliation":[{"name":"COMSATS University,Department of Computer Science,Abbottabad"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sara","family":"Ali","sequence":"additional","affiliation":[{"name":"National University of Sciences and Technology,Department of Robotics,Islamabad,Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"U.S. Khan","family":"Muhammad","sequence":"additional","affiliation":[{"name":"COMSATS University,Department of Computer Science,Islamabad Campus"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Jawad","sequence":"additional","affiliation":[{"name":"COMSATS University,Department of Electrical Engineering,Lahore Campus"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mazhar","family":"Ali","sequence":"additional","affiliation":[{"name":"COMSATS University,Department of Computer Science,Islamabad Campus"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raheel","family":"Nawaz","sequence":"additional","affiliation":[{"name":"Manchester Metropolitan University,School of Computing, Mathematics and Digital Technology,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","volume":"14","author":"hinton","year":"2012","journal-title":"Neural networks for machine learning lecture 6a overview of mini-batch gradient descent"},{"key":"ref11","article-title":"Adadelta: an adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv preprint arXiv 1212 5701"},{"key":"ref12","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref13","article-title":"On the convergence of adam and beyond","author":"reddi","year":"2019","journal-title":"arXiv preprint arXiv 1904 09099"},{"key":"ref14","article-title":"diffGrad: An Optimization Method for Convolutional Neural Networks","author":"dubey","year":"2019","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"ref15","article-title":"Adabatch: Adaptive batch sizes for training deep neural networks","author":"devarakonda","year":"2017","journal-title":"arXiv preprint arXiv 1712 02029"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref3","article-title":"Neural networks for machine learning lecture 6a overview of mini-batch gradient descent","volume":"14","author":"hinton","year":"2012","journal-title":"CITE"},{"key":"ref6","article-title":"An overview of gradient descent optimization algorithms","author":"ruder","year":"2016","journal-title":"arXiv preprint arXiv 1609 04802"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2912200"},{"key":"ref8","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":"ref7","first-page":"71","article-title":"Stochastic gradient descent for non-smooth optimization: Convergence results and optimal averaging schemes","author":"shamir","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref2","article-title":"An overview of gradient descent optimization algorithms","author":"ruder","year":"2016","journal-title":"arXiv preprint arXiv 1609 04802"},{"key":"ref9","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":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"}],"event":{"name":"2020 14th International Conference on Innovations in Information Technology (IIT)","location":"Al Ain, United Arab Emirates","start":{"date-parts":[[2020,11,17]]},"end":{"date-parts":[[2020,11,18]]}},"container-title":["2020 14th International Conference on Innovations in Information Technology (IIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9298898\/9298970\/09299013.pdf?arnumber=9299013","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T17:40:22Z","timestamp":1670262022000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9299013\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,17]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/iit50501.2020.9299013","relation":{},"subject":[],"published":{"date-parts":[[2020,11,17]]}}}