{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:42:38Z","timestamp":1762368158708,"version":"build-2065373602"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"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":[[2025,8,31]]},"DOI":"10.1109\/mlsp62443.2025.11204263","type":"proceedings-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:15:52Z","timestamp":1761326152000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Fast and Robust Training of Deep Learning Models with Multiplicative Adagrad"],"prefix":"10.1109","author":[{"given":"Manos","family":"Kirtas","sequence":"first","affiliation":[{"name":"Aristotle University of Thessaloniki,Computational Intelligence and Deep Learning Group,Dept. of Informatics,Thessaloniki,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikolaos","family":"Passalis","sequence":"additional","affiliation":[{"name":"Aristotle University of Thessaloniki,Computational Intelligence and Deep Learning Group,Dept. of Chemical Engineering,Thessaloniki,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anastasios","family":"Tefas","sequence":"additional","affiliation":[{"name":"Aristotle University of Thessaloniki,Computational Intelligence and Deep Learning Group,Dept. of Informatics,Thessaloniki,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"7","key":"ref1","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":"ref2","article-title":"On the convergence of adam and beyond","volume-title":"6th International Conference on Learning Representations","author":"Reddi","year":"2018"},{"key":"ref3","article-title":"On the variance of the adaptive learning rate and beyond","volume-title":"8th International Conference on Learning Representations","author":"Liu","year":"2020"},{"key":"ref4","article-title":"Large batch training of convolutional networks","author":"You","year":"2017","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.4086\/toc.2012.v008a006"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022869011914"},{"key":"ref7","article-title":"Algorithms for non-negative matrix factorization","volume":"13","author":"Lee","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"21370","article-title":"On the distance between two neural networks and the stability of learning","volume":"33","author":"Bernstein","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","first-page":"13319","article-title":"Learning compositional functions via multiplicative weight updates","volume":"33","author":"Bernstein","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","first-page":"1352","article-title":"ReZero is All You Need: Fast Convergence at Large Depth","author":"Bachlechner","year":"2021","journal-title":"37th Conf. on Uncertainty in Artificial Intelligence"},{"key":"ref11","article-title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","volume-title":"International Conference on Learning Representations","author":"Zhang","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-74627-7_35"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1063\/5.0169810"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref15","first-page":"244","article-title":"On the optimization of deep networks: Implicit acceleration by overparameterization","volume-title":"Proceedings of the 35th International Conf. on Machine Learning. 2018","volume":"80","author":"Arora"},{"key":"ref16","article-title":"Qualitatively characterizing neural network optimization problems","author":"Goodfellow","year":"2014","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2479223"},{"key":"ref18","first-page":"6748","article-title":"Learning by turning: Neural architecture aware optimisation","volume-title":"Proceedings of the 38th International Conf. on Machine Learning","volume":"139","author":"Liu","year":"2021"},{"key":"ref19","first-page":"560","article-title":"signsgd: Compressed optimisation for non-convex problems","author":"Bernstein","year":"2018","journal-title":"International Conf. on Machine Learning. PMLR"}],"event":{"name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","start":{"date-parts":[[2025,8,31]]},"location":"Istanbul, Turkiye","end":{"date-parts":[[2025,9,3]]}},"container-title":["2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11204201\/11204202\/11204263.pdf?arnumber=11204263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:37:30Z","timestamp":1762367850000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11204263\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/mlsp62443.2025.11204263","relation":{},"subject":[],"published":{"date-parts":[[2025,8,31]]}}}