{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:08:47Z","timestamp":1777129727746,"version":"3.51.4"},"reference-count":144,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"HKRGC"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076067"],"award-info":[{"award-number":["62076067"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61977038"],"award-info":[{"award-number":["61977038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Thousand Talents Plan of Jiangxi Province","award":["jxsq2019201124"],"award-info":[{"award-number":["jxsq2019201124"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Grants Council Joint Research Scheme","award":["HKUST635\/20"],"award-info":[{"award-number":["HKUST635\/20"]}]},{"name":"Hong Kong Research Grant Council","award":["16308321"],"award-info":[{"award-number":["16308321"]}]},{"name":"Hong Kong Research Grant Council","award":["16303817"],"award-info":[{"award-number":["16303817"]}]},{"name":"Hong Kong Research Grant Council","award":["ITF UIM\/390"],"award-info":[{"award-number":["ITF UIM\/390"]}]},{"name":"Tencent AI Lab"},{"name":"Si Family Foundation"},{"DOI":"10.13039\/100016909","name":"Microsoft Research Asia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016909","id-type":"DOI","asserted-by":"publisher"}]},{"name":"HKRGC Collaborative Research Fund","award":["C6021-19EF"],"award-info":[{"award-number":["C6021-19EF"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,2,1]]},"DOI":"10.1109\/tpami.2022.3168881","type":"journal-article","created":{"date-parts":[[2022,4,22]],"date-time":"2022-04-22T19:37:09Z","timestamp":1650656229000},"page":"1749-1765","source":"Crossref","is-referenced-by-count":11,"title":["Exploring Structural Sparsity of Deep Networks Via Inverse Scale Spaces"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6595-6893","authenticated-orcid":false,"given":"Yanwei","family":"Fu","sequence":"first","affiliation":[{"name":"School of Data Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8641-3097","authenticated-orcid":false,"given":"Chen","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2673-9693","authenticated-orcid":false,"given":"Donghao","family":"Li","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuyuan","family":"Zhong","sequence":"additional","affiliation":[{"name":"School of Data Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinwei","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Data Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1719-3358","authenticated-orcid":false,"given":"Jinshan","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5814-1162","authenticated-orcid":false,"given":"Yuan","family":"Yao","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2502579"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_14"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref5","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref7","first-page":"134","article-title":"For valid generalization, the size of the weights is more important than the size of the network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bartlett"},{"key":"ref8","first-page":"6241","article-title":"Spectrally-normalized margin bounds for neural networks","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Bartlett"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaz007"},{"key":"ref10","article-title":"The role of over-parametrization in generalization of neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Neyshabur"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1806579115"},{"key":"ref12","first-page":"242","article-title":"A convergence theory for deep learning via over-parameterization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Allen-Zhu"},{"key":"ref13","first-page":"1675","article-title":"Gradient descent finds global minima of deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Du"},{"key":"ref14","article-title":"Spurious valleys in two-layer neural network optimization landscapes","volume":"20","author":"Venturi","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref15","article-title":"Understanding over-parameterization in generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Balaji"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"ref17","article-title":"Memory bounded deep convolutional networks","author":"Collins","year":"2014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/18.959265"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2004.834793"},{"issue":"7","key":"ref20","first-page":"2541","article-title":"On model selection consistency of lasso","volume":"1","author":"Zhao","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s00365-006-0663-2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2927563"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00532.x"},{"key":"ref25","first-page":"3958","article-title":"Combined group and exclusive sparsity for deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yoon"},{"key":"ref26","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/309"},{"key":"ref28","article-title":"Incremental network quantization: Towards lossless cnns with low-precision weights","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.88"},{"key":"ref30","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref31","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"Frankle","year":"2018","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref32","article-title":"Stabilizing the lottery ticket hypothesis","author":"Frankle","year":"2019"},{"key":"ref33","first-page":"4932","article-title":"One ticket to win them all: Generalizing lottery ticket initializations across datasets and optimizers","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Morcos"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.4310\/CMS.2006.v4.n1.a7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2016.01.002"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/11567646_3"},{"key":"ref37","first-page":"2047","article-title":"A unified dynamic approach to sparse model selection","volume-title":"Proc. 21st 21st Int. Conf. Artif. Intell. Statist.","author":"Huang"},{"key":"ref38","first-page":"3369","article-title":"Split LBI: An iterative regularization path with structural sparsity","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2017.12.004"},{"key":"ref40","first-page":"10 820","article-title":"Good subnetworks provably exist: Pruning via greedy forward selection","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ye"},{"key":"ref41","article-title":"Rethinking the value of network pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref42","first-page":"3315","article-title":"Dessilbi: Exploring structural sparsity of deep networks via differential inclusion paths","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fu"},{"key":"ref43","volume-title":"Problem Complexity and Method Efficiency in Optimization","author":"Nemirovski","year":"1978"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6377(02)00231-6"},{"key":"ref45","article-title":"Tutorial: Mirror descent algorithms for large-scale deterministic and stochastic convex optimization","author":"Nemirovski","year":"2012","journal-title":"Conf. Learn. Theory"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1137\/110848864"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1137\/120894464"},{"issue":"1","key":"ref48","first-page":"5312","article-title":"A differential equation for modeling nesterovs accelerated gradient method: Theory and insights","volume":"17","author":"Su","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref49","first-page":"2845","article-title":"Accelerated mirror descent in continuous and discrete time","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krichene"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3087480"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1137\/070703983"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1137\/040605412"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-09-02242-X"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2009.2016018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66179-7_13"},{"key":"ref56","first-page":"5912","article-title":"MSplit LBI: Realizing feature selection and dense estimation simultaneously in few-shot and zero-shot learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao","year":"2018"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2817205"},{"key":"ref58","first-page":"3901","article-title":"iSplit LBI: Individualized partial ranking with ties via split LBI","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5359"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01438-y"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3182\/20120711-3-BE-2027.00310"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1137\/110836936"},{"key":"ref64","first-page":"2816","article-title":"Bregman alternating direction method of multipliers","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref65","first-page":"2722","article-title":"Training neural networks without gradients: A scalable ADMM approach","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Taylor"},{"issue":"199","key":"ref66","first-page":"1","article-title":"On admm in deep learning: Convergence and saturation-avoidance","volume":"22","author":"Zeng","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-018-0757-z"},{"key":"ref68","first-page":"1559","article-title":"Admm and accelerated admm as continuous dynamical systems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Franca"},{"key":"ref69","volume-title":"Convex Analysis","author":"Rockafellar","year":"2015"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-1740-8"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1198\/016214503000125"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1079120128"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1214\/009053605000000255"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2927563"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2016.01.002"},{"key":"ref77","first-page":"2047","article-title":"A unified dynamic approach to sparse model selection","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Huang"},{"key":"ref78","first-page":"3369","article-title":"Split LBI: An iterative regularization path with structural sparsity. advances in neural information processing systems","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref79","first-page":"598","article-title":"Optimal brain damage","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"LeCun"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.553"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00508"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00159"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s00365-006-0663-2"},{"key":"ref84","first-page":"3819","article-title":"Functional gradient boosting based on residual network perception","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nitanda"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.2307\/1267352"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref87","article-title":"Playing the lottery with rewards and multiple languages: Lottery tickets in RL and NLP","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref88","first-page":"15 834","article-title":"The lottery ticket hypothesis for pre-trained BERT networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.259"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01191"},{"key":"ref91","first-page":"6682","article-title":"Proving the lottery ticket hypothesis: Pruning is all you need","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Malach"},{"key":"ref92","first-page":"3259","article-title":"Linear mode connectivity and the lottery ticket hypothesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Frankle"},{"key":"ref93","first-page":"2925","article-title":"Logarithmic pruning is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Orseau"},{"key":"ref94","first-page":"2599","article-title":"Optimal lottery tickets via subset sum: Logarithmic over-parameterization is sufficient","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pensia"},{"key":"ref95","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zoph"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00257"},{"key":"ref98","article-title":"Darts: Differentiable architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref99","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cai"},{"key":"ref100","first-page":"2902","article-title":"Large-scale evolution of image classifiers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Real"},{"key":"ref101","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pham"},{"key":"ref102","first-page":"550","article-title":"Understanding and simplifying one-shot architecture search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bender"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"ref104","article-title":"Visualizing higher-layer features of a deep network","volume":"1341","author":"Erhan","year":"2009"},{"key":"ref105","first-page":"7313","article-title":"Global convergence of block coordinate descent in deep learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Zeng"},{"key":"ref106","first-page":"87","article-title":"Une propri\u00e9t\u00e9 topologique des sous-ensembles analytiques r\u00e9els","volume":"117","author":"\u0141ojasiewicz","year":"1963"},{"key":"ref107","article-title":"Convergence of a relaxed variable splitting method for learning sparse neural networks via $\\ell _{1}$\u21131, $\\ell _{0}$\u21130, and transformed-$\\ell _{1}$\u21131 penalties","author":"Xue","year":"2018"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-011-0484-9"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02431-3"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.3389\/fams.2020.575073"},{"key":"ref111","article-title":"A surprising linear relationship predicts test performance in deep networks","author":"Liao","year":"2018"},{"key":"ref112","article-title":"Path-SGD: Path-normalized optimization in deep neural networks","author":"Neyshabur","year":"2015"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref115","article-title":"Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Geirhos"},{"key":"ref116","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Han"},{"key":"ref117","article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","author":"Zhu","year":"2017"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"ref119","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref121","article-title":"Pruning filters for efficient convnets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00289"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00804"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403126"},{"key":"ref125","article-title":"Simple and efficient architecture search for convolutional neural networks","author":"Elsken","year":"2017"},{"key":"ref126","first-page":"10 656","article-title":"Splitting steepest descent for growing neural architectures","volume":"32","author":"Wu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref127","article-title":"Energy-aware neural architecture optimization with fast splitting steepest descent","author":"Wang","year":"2019"},{"key":"ref128","article-title":"Firefly neural architecture descent: A general approach for growing neural networks","author":"Wu","year":"2021"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-31247-1"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.5802\/aif.1384"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.5802\/aif.1638"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1137\/050644641"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1137\/060670080"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-8134-0"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-03718-8"},{"key":"ref136","volume-title":"Ensembles Semi-Analytiques","author":"\u0141ojasiewicz","year":"1965"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-2008-4"},{"key":"ref138","article-title":"An introduction to o-minimal geometry","author":"Coste","year":"1999"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1090\/S0273-0979-1986-15468-6"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1215\/S0012-7094-96-08416-1"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1137\/20m1357500"},{"key":"ref142","article-title":"Structural compression of convolutional neural networks based on greedy filter pruning","author":"Abbasi-Asl","year":"2017"},{"key":"ref143","article-title":"Striving for simplicity: The all convolutional net","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Springenberg"},{"key":"ref144","article-title":"Learning Multiple Layers of Features From Tiny Images","author":"Krizhevsky","year":"2009"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10008914\/09762064.pdf?arnumber=9762064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:19:43Z","timestamp":1705958383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9762064\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,1]]},"references-count":144,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3168881","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,1]]}}}