{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T19:14:43Z","timestamp":1790709283605,"version":"4.1.0"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"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":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9412162","type":"proceedings-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T02:15:54Z","timestamp":1620267354000},"page":"1566-1573","source":"Crossref","is-referenced-by-count":11,"title":["Learning sparse deep neural networks using efficient structured projections on convex constraints for green AI"],"prefix":"10.1109","author":[{"given":"Michel","family":"Barlaud","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frederic","family":"Guyard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2270","article-title":"Learning the number of neurons in deep networks","author":"alvarez","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref38","first-page":"662","article-title":"Less is more: Towards compact cnns","author":"zhou","year":"0","journal-title":"European Conference on Computer Vision"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9569-8_10"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/0716071"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24033\/bsmf.1625"},{"key":"ref30","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref37","first-page":"353","article-title":"Complexity analysis of the lasso regularization path","author":"mairal","year":"0","journal-title":"Proceedings of the 29th International Conference on Machine Learning (ICML-12)"},{"key":"ref36","first-page":"1391","article-title":"The entire regularization path for the support vector machine","volume":"5","author":"hastie","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"ref35","author":"sra","year":"2012","journal-title":"Optimization for Machine Learning"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15883-4_27"},{"key":"ref60","author":"grochowski","year":"2006","journal-title":"Energy per instruction trends in intel &#x00AE; microprocessors"},{"key":"ref28","article-title":"Matrix completion by truncated nuclear norm regularization","author":"zhang","year":"2012","journal-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref27"},{"key":"ref29","first-page":"435","article-title":"Dropout as a low-rank regularizer for matrix factorization","author":"cavazza","year":"0","journal-title":"International Conference on Artificial Intelligence and Statistics (AISTATS)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2896880"},{"key":"ref1","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.02.029"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00532.x"},{"key":"ref24"},{"key":"ref23","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref25"},{"key":"ref50","first-page":"339","article-title":"Multi-task feature learning via efficient 12, 1-norm minimization","author":"liu","year":"0","journal-title":"Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence ser UAI &#x2018;09"},{"key":"ref51"},{"key":"ref59"},{"key":"ref58"},{"key":"ref57","author":"lecun","year":"0","journal-title":"The MNIST Database of Handwritten Digits"},{"key":"ref56","first-page":"1","article-title":"a method for stochastic optimization","author":"kingma","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref55","first-page":"3597","article-title":"Deconstructing lottery tickets: Zeros, signs, and the supermask","volume":"32","author":"zhou","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref54","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"frankle","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00532.x"},{"key":"ref52","first-page":"4635","volume":"65","author":"barlaud","year":"2017","journal-title":"Classification and regression using an outer approximation projection-gradient method"},{"key":"ref10","author":"schwartz","year":"2019","journal-title":"Green ai"},{"key":"ref11","first-page":"2148","article-title":"Predicting parameters in deep learning","author":"denil","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref40","first-page":"304","article-title":"Data-driven sparse structure selection for deep neural networks","author":"huang","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v033.i01"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1201\/b18401"},{"key":"ref14","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"3878","article-title":"Learning sparse neural networks via sensitivity-driven regularization","author":"tartaglione","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref16"},{"key":"ref17","article-title":"Learning-compression algorithms for neural net pruning","author":"carreira-perpi\u00f1\u00e1n","year":"2018","journal-title":"The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11021-5_19"},{"key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021745"},{"key":"ref7","article-title":"Are very deep neural networks feasible on mobile devices","author":"rallapalli","year":"2016","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-019-01401-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1355"},{"key":"ref46","article-title":"Toward compact convnets via structure-sparsity regularized filter pruning","author":"lin","year":"2019","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"ref45","first-page":"930","article-title":"Ordered weighted 11 regularized regression with strongly correlated covariates: Theoretical aspects","author":"figueiredo","year":"2016","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref48","first-page":"272","article-title":"Efficient projections onto the 1 1-ball for learning in high dimensions","author":"duchi","year":"0","journal-title":"Proceedings of the 25th International Conference on Machine Learning"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0946-6"},{"key":"ref42","author":"zhang","year":"2018","journal-title":"Learning to share Simultaneous parameter tying and sparsification in deep learning"},{"key":"ref41","first-page":"3958","article-title":"Combined group and exclusive sparsity for deep neural networks","volume":"70","author":"yoon","year":"0","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/SSP.2018.8450819"},{"key":"ref43","first-page":"1041","article-title":"Representational similarity learning with application to brain networks","author":"oswal","year":"0","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","location":"Milan, Italy","start":{"date-parts":[[2021,1,10]]},"end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09412162.pdf?arnumber=9412162","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:39Z","timestamp":1652197239000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9412162\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9412162","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}