{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:06:53Z","timestamp":1737176813172,"version":"3.33.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10825352","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"1442-1449","source":"Crossref","is-referenced-by-count":0,"title":["NysAct: A Scalable Preconditioned Gradient Descent using Nystr\u00f6m Approximation"],"prefix":"10.1109","author":[{"given":"Hyunseok","family":"Seung","sequence":"first","affiliation":[{"name":"University of Georgia,Department of Statistics,Athens,USA"}]},{"given":"Jaewoo","family":"Lee","sequence":"additional","affiliation":[{"name":"University of Georgia,School of Computing,Athens,USA"}]},{"given":"Hyunsuk","family":"Ko","sequence":"additional","affiliation":[{"name":"Hanyang University,School of Electrical Engineering,Ansan,South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","key":"ref3"},{"article-title":"Shampoo: Preconditioned stochastic tensor optimization","volume-title":"International Conference on Machine Learning","author":"Gupta","key":"ref4"},{"key":"ref5","article-title":"Practical quasi-newton methods for training deep neural networks","author":"Goldfarb","year":"2020","journal-title":"Neural Information Processing Systems"},{"article-title":"Sophia: A scalable stochastic second-order optimizer for language model pre-training","volume-title":"International Conference on Learning Representations","author":"Liu","key":"ref6"},{"key":"ref7","article-title":"Better SGD using second-order momentum","author":"Tran","year":"2022","journal-title":"Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/23m1575330"},{"article-title":"Optimizing neural networks with kronecker-factored approximate curvature","volume-title":"International Conference on Machine Learning","author":"Martens","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17275"},{"article-title":"Gradient descent on neurons and its link to approximate second-order optimization","volume-title":"International Conference on Machine Learning","author":"Benzing","key":"ref11"},{"key":"ref12","article-title":"Fixed-rank approximation of a positive-semidefinite matrix from streaming data","author":"Tropp","year":"2017","journal-title":"Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20779"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009","journal-title":"Citeseer, Tech. Rep."},{"key":"ref16","article-title":"Using the nystr\u00f6m method to speed up kernel machines","author":"Williams","year":"2000","journal-title":"Neural Information Processing Systems"},{"article-title":"Efficient full-matrix adaptive regularization","volume-title":"International Conference on Machine Learning","author":"Agarwal","key":"ref17"},{"key":"ref18","article-title":"M-FAC: Efficient matrix-free approximations of second-order information","volume-title":"Neural Information Processing Systems","author":"Frantar","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01327"},{"article-title":"Eva: Practical second-order optimization with kronecker-vectorized approximation","volume-title":"International Conference on Learning Representations","author":"Zhang","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1093\/imamat\/6.3.222"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/13.3.317"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1970-0258249-6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1970-0274029-X"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1137\/21M1466244"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"article-title":"Sgdr: Stochastic gradient descent with warm restarts","volume-title":"International Conference on Learning Representations","author":"Loshchilov","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International Conference on Machine Learning","author":"Touvron","key":"ref30"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","start":{"date-parts":[[2024,12,15]]},"location":"Washington, DC, USA","end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10825352.pdf?arnumber=10825352","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:46:39Z","timestamp":1737099999000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825352\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825352","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}