{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T08:02:20Z","timestamp":1770019340150,"version":"3.49.0"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Bharti School of Telecom Technology and Management, IIT, Delhi"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1109\/tai.2022.3153593","type":"journal-article","created":{"date-parts":[[2022,2,25]],"date-time":"2022-02-25T15:34:54Z","timestamp":1645803294000},"page":"304-314","source":"Crossref","is-referenced-by-count":4,"title":["Projective Fisher Information for Natural Gradient Descent"],"prefix":"10.1109","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3117-2377","authenticated-orcid":false,"given":"Piyush","family":"Kaul","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Indian Institute of Technology - Delhi, New Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brejesh","family":"Lall","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Indian Institute of Technology - Delhi, New Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"127","article-title":"Neural learning in structured parameter spaces-natural Riemannian gradient","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Amari","year":"1997"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017746"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1090\/mmono\/191"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref5","article-title":"Fisher information and natural gradient learning of random deep networks","author":"Amari","year":"2018"},{"issue":"4","key":"ref6","first-page":"322","article-title":"Statistical neurodynamics of deep networks: Geometry of signal spaces, nonlinear theory and its applications","volume":"10","author":"Amari","year":"2019","journal-title":"IEICE"},{"key":"ref7","volume-title":"Probability, Random Variables, and Stochastic Processes","author":"Papoulis","year":"2002"},{"key":"ref8","first-page":"604","article-title":"Fast large-scale optimization by unifying stochastic gradient and quasi-newton methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2014"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/0471221082"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1992.287114"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref12","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref15","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow","year":"2014"},{"key":"ref16","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref17","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky","year":"2012"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","first-page":"19","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Liu","year":"2018"},{"key":"ref20","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref23","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amodei","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2020.2984991"},{"key":"ref25","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2737479"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2991766"},{"key":"ref28","article-title":"Multivariate Gaussian variational inference by natural gradient descent","author":"Barfoot","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3813403"},{"key":"ref30","article-title":"Tractable structured natural gradient descent using local parameterizations","author":"Lin","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/math9131470"},{"key":"ref32","first-page":"2408","article-title":"Optimizing neural networks with Kronecker-factored approximate curvature","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Martens","year":"2015"},{"key":"ref33","first-page":"573","article-title":"A Kronecker-factored approximate Fisher matrix for convolution layers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Grosse","year":"2016"},{"key":"ref34","article-title":"New insights and perspectives on the natural gradient method","author":"Martens","year":"2014"},{"key":"ref35","first-page":"9550","article-title":"Fast approximate natural gradient descent in a Kronecker factored eigenbasis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"George","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00902"},{"key":"ref37","article-title":"Practical quasi-newton methods for training deep neural networks","author":"Goldfarb","year":"2020"},{"key":"ref38","article-title":"Kronecker-factored quasi-newton methods for convolutional neural networks","author":"Ren","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01264"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3004354"},{"key":"ref41","article-title":"Projective Kronecker factored approximate curvature: Implementation in pytorch","author":"Kaul"},{"key":"ref42","first-page":"36","volume-title":"Analysis, Manifolds and Physics (Revised Edition)","volume":"35","author":"Choquet-Bruhat","year":"1982"},{"key":"ref43","volume-title":"Riemannian Manifolds: An Introduction to Curvature","volume":"176","author":"Lee","year":"2006"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2919705"},{"issue":"1","key":"ref45","first-page":"1","article-title":"An elementary proof of the Johnson-Lindenstrauss lemma","volume":"22","author":"Dasgupta","year":"1999"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref47","article-title":"MNIST handwritten digit database","author":"LeCun","year":"2010"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_32"},{"key":"ref49","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref51","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10081152\/09721554.pdf?arnumber=9721554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:08:43Z","timestamp":1755911323000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9721554\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":53,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tai.2022.3153593","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4]]}}}