{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:46:27Z","timestamp":1740102387441,"version":"3.37.3"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-22-1-0296"],"award-info":[{"award-number":["W911NF-22-1-0296"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,4]]},"DOI":"10.23919\/eusipco58844.2023.10289761","type":"proceedings-article","created":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T17:55:44Z","timestamp":1698861344000},"page":"1245-1249","source":"Crossref","is-referenced-by-count":1,"title":["Assessment of a Two-Step Integration Method as an Optimizer for Deep Learning"],"prefix":"10.23919","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8501-0907","authenticated-orcid":false,"given":"Paul","family":"Rodriguez","sequence":"first","affiliation":[{"name":"Pontifical Catholic University of Peru,Department of Electrical Engineering,Lima,Peru"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Eadam optimizer How ? impact adam","year":"2020","author":"yuan","key":"ref13"},{"key":"ref12","article-title":"Quasi-hyperbolic momentum and adam for deep learning","author":"ma","year":"0","journal-title":"Int'l Conf on Learning Representations (ICLR)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-022-06215-7"},{"key":"ref14","first-page":"18795","article-title":"Adabelief optimizer: Adapting stepsizes by the belief in observed gradients","volume":"33","author":"zhuang","year":"2020","journal-title":"Adv in Neural Information Proc Syst"},{"journal-title":"TensorFlow Large-Scale Machine Learning on Heterogeneous Systems","year":"2015","author":"abadi","key":"ref31"},{"key":"ref30","article-title":"Deepobs: A deep learning optimizer benchmark suite","author":"schneider","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref11","article-title":"Adaptive gradient methods with dynamic bound of learning rate","author":"luo","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01602"},{"key":"ref10","article-title":"On the convergence of adam and beyond","author":"reddi","year":"0","journal-title":"International Conference on Learning Representations"},{"journal-title":"Simulations for SGD variants","year":"0","author":"rodriguez","key":"ref32"},{"journal-title":"Gradient Flows in Metric Spaces and in the Space of Probability Measures","year":"0","author":"ambrosio","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/9781119121534"},{"key":"ref17","article-title":"An improved analysis of stochastic gradient descent with momentum","author":"liu","year":"2020","journal-title":"Int'l Conf Neural Info Process Syst"},{"journal-title":"Keep the gradients flowing Using gradient flow to study sparse network optimization","year":"2021","author":"tessera","key":"ref16"},{"key":"ref19","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"ICLRE"},{"key":"ref18","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref24","article-title":"Adaptive gradient methods with dynamic bound of learning rate","author":"luo","year":"2018","journal-title":"Int Conf on Learning Representations"},{"key":"ref23","article-title":"An overview of gradient descent optimization algorithms","volume":"abs 1609 4747","author":"ruder","year":"2016","journal-title":"CoRR"},{"key":"ref26","first-page":"421","author":"bottou","year":"2012","journal-title":"Stochastic Gradient Descent Tricks"},{"key":"ref25","article-title":"Online algorithms and stochastic approximations","author":"bottou","year":"1998","journal-title":"Online Learning and Neural Networks"},{"key":"ref20","first-page":"10096","article-title":"Efficientnetv2: Smaller models and faster training","volume":"139","author":"tan","year":"2021","journal-title":"ICML"},{"key":"ref22","first-page":"1","article-title":"Improving the stochastic gradient descent's test accuracy by manipulating the L? norm of its gradient approximation","author":"rodriguez","year":"2023","journal-title":"IEEE ICASSP"},{"journal-title":"On empirical comparisons of optimizers for deep learning","year":"2019","author":"choi","key":"ref21"},{"journal-title":"Statistical Digital Signal Processing and Modeling","year":"1996","author":"hayes","key":"ref28"},{"key":"ref27","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":"ref29","article-title":"Note on learning rate schedules for stochastic optimization","volume":"3","author":"darken","year":"1990","journal-title":"Advances in neural information processing systems"},{"journal-title":"ADADELTA An Adaptive Learning Rate Method","year":"2012","author":"zeiler","key":"ref8"},{"journal-title":"Neural networks for machine learning lecture 6a overview of mini-batch gradient descent","year":"2012","author":"hinton","key":"ref7"},{"key":"ref9","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Int'l Conf on Learning Representations (ICLR)"},{"key":"ref4","first-page":"372","article-title":"A method of solving a convex programming problem with convergence rate o(1\/k)2","volume":"27","author":"nesterov","year":"1983","journal-title":"Soviet Mathematics Doklady"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(64)90137-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/321296.321305"},{"key":"ref5","article-title":"Integration methods and optimization algorithms","volume":"30","author":"scieur","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2023 31st European Signal Processing Conference (EUSIPCO)","start":{"date-parts":[[2023,9,4]]},"location":"Helsinki, Finland","end":{"date-parts":[[2023,9,8]]}},"container-title":["2023 31st European Signal Processing Conference (EUSIPCO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10289698\/10289713\/10289761.pdf?arnumber=10289761","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T19:20:31Z","timestamp":1701112831000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10289761\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,4]]},"references-count":33,"URL":"https:\/\/doi.org\/10.23919\/eusipco58844.2023.10289761","relation":{},"subject":[],"published":{"date-parts":[[2023,9,4]]}}}