{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:42:40Z","timestamp":1775144560918,"version":"3.50.1"},"reference-count":280,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"A*STAR Centre for Frontier AI Research"},{"name":"CFAR Internship Award and Research Excellence"},{"DOI":"10.13039\/501100005049","name":"A*STAR Science and Engineering Research Council","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005049","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Maritime AI Research Programme","award":["SMI-2022-MTP-06"],"award-info":[{"award-number":["SMI-2022-MTP-06"]}]},{"DOI":"10.13039\/501100018889","name":"Singapore Maritime Institute","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100018889","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tpami.2023.3334614","type":"journal-article","created":{"date-parts":[[2023,11,28]],"date-time":"2023-11-28T19:12:43Z","timestamp":1701198763000},"page":"2900-2919","source":"Crossref","is-referenced-by-count":230,"title":["Structured Pruning for Deep Convolutional Neural Networks: A Survey"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2257-6073","authenticated-orcid":false,"given":"Yang","family":"He","sequence":"first","affiliation":[{"name":"Centre for Frontier AI Research (CFAR), Agency for Science Technology and Research (A*STAR), Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1697-1986","authenticated-orcid":false,"given":"Lingao","family":"Xiao","sequence":"additional","affiliation":[{"name":"Centre for Frontier AI Research (CFAR), Agency for Science Technology and Research (A*STAR), Singapore"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Han"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.2100463"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref6","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Simonyan"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref10","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":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref12","first-page":"1269","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Denton"},{"key":"ref13","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NeurIPS Deep Learn. Represent. Learn. Workshop","author":"Hinton"},{"key":"ref14","article-title":"Pruning filters for efficient convnets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00874"},{"key":"ref17","first-page":"2286","article-title":"ConVit: Improving vision transformers with soft convolutional inductive biases","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01174"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01739-w"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01627"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2021.0068"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993472"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3578938"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s40745-022-00389-6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.23919\/CCC50068.2020.9189610"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10489-1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3182659"},{"issue":"241","key":"ref32","first-page":"1","article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","volume":"22","author":"Hoefler","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/I-SMAC55078.2022.9987264"},{"key":"ref34","first-page":"129","article-title":"What is the state of neural network pruning?","volume-title":"Proc. Mach. Learn. Syst.","author":"Blalock"},{"key":"ref35","article-title":"A survey on methods and theories of quantized neural networks","author":"Guo","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107281"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055564"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3447582"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2021.3079985"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3100554"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.045"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-018-0059-3"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765695"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700789"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2022.3153408"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24425\/bpas.2018.125927"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WF-IoT48130.2020.9221198"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11060945"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3039858"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"ref53","first-page":"20863","article-title":"RED: Looking for redundancies for data-freestructured compression of deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yvinec"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3179616"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/525"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01467"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3156047"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084856"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_28"},{"key":"ref62","first-page":"24604","article-title":"Chip: Channel independence-based pruning for compact neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sui"},{"key":"ref63","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"Hu","year":"2016"},{"key":"ref64","first-page":"9356","article-title":"DropNet: Reducing neural network complexity via iterative pruning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3124284"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/431"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref68","first-page":"1607","article-title":"Approximated oracle filter pruning for destructive CNN width optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ding"},{"key":"ref69","first-page":"10820","article-title":"Good subnetworks provably exist: Pruning via greedy forward selection","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ye"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00958"},{"key":"ref71","first-page":"883","article-title":"Discrimination-aware channel pruning for deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhuang"},{"key":"ref72","article-title":"Provable filter pruning for efficient neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liebenwein"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_15"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref75","article-title":"Gate decorator: Global filter pruning method for accelerating deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"You"},{"key":"ref76","first-page":"9865","article-title":"Neuron-level structured pruning using polarization regularizer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhuang"},{"key":"ref77","article-title":"Rethinking the smaller-norm-less-informative assumption in channel pruning of convolution layers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ye"},{"key":"ref78","first-page":"5122","article-title":"Operation-aware soft channel pruning using differentiable masks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kang"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_38"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_19"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00290"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00197"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00519"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00447"},{"key":"ref85","first-page":"10936","article-title":"SCOP: Scientific control for reliable neural network pruning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tang"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00932"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3106917"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3147269"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00159"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2950105"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157329"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00721"},{"key":"ref93","first-page":"19637","article-title":"Only train once: A one-shot neural network training and pruning framework","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref94","article-title":"Neural pruning via growing regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref95","article-title":"Pruning convolutional neural networks for resource efficient inference","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Molchanov"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref97","first-page":"5113","article-title":"Collaborative channel pruning for deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peng"},{"key":"ref98","first-page":"6566","article-title":"Eigendamage: Structured pruning in the kronecker-factored eigenbasis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref99","first-page":"7021","article-title":"Group Fisher pruning for practical network compression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00372"},{"key":"ref101","article-title":"SOSP: Efficiently capturing global correlations by second-order structured pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nonnenmacher"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00289"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00340"},{"key":"ref104","first-page":"1135","article-title":"Compressing neural networks using the variational information bottleneck","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dai"},{"key":"ref105","first-page":"3290","article-title":"Bayesian compression for deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Louizos"},{"key":"ref106","first-page":"6778","article-title":"Structured Bayesian pruning via log-normal multiplicative noise","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Neklyudov"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00508"},{"key":"ref108","article-title":"Training structured neural networks through manifold identification and variance reduction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00061"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_34"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3045153"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3063265"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_29"},{"key":"ref114","first-page":"5544","article-title":"Soft threshold weight reparameterization for learnable sparsity","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kusupati"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/309"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/336"},{"key":"ref117","article-title":"Dynamic model pruning with feedback","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01197"},{"key":"ref119","article-title":"Dynamic sparse graph for efficient deep learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3035028"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979517"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_38"},{"key":"ref123","article-title":"Runtime neural pruning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref124","article-title":"Dynamic channel pruning: Feature boosting and suppression","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gao"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00498"},{"key":"ref126","first-page":"14747","article-title":"Storage efficient and dynamic flexible runtime channel pruning via deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00528"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01213"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01194"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00630"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01203"},{"key":"ref133","first-page":"25656","article-title":"Topology-aware network pruning using multi-stage graph embedding and reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5924"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00357"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00161"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_35"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_36"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/449"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00208"},{"key":"ref141","first-page":"760","article-title":"Network pruning via transformable architecture search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00054"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_20"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3149332"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3165123"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3161284"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3192169"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00339"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/94"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/667"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3069970"},{"key":"ref152","article-title":"Rethinking the value of network pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref153","article-title":"Drawing early-bird tickets: Towards more efficient training of deep networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"You"},{"key":"ref154","article-title":"Prospect pruning: Finding trainable weights at initialization using meta-gradients","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Alizadeh"},{"key":"ref155","article-title":"Winning the lottery ahead of time: Efficient early network pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rachwan"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01193"},{"key":"ref157","article-title":"Plant\u2019n\u2019seek: Can you find the winning ticket?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fischer"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_40"},{"key":"ref159","article-title":"Proving the lottery ticket hypothesis for convolutional neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cunha"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00029"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01403"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_16"},{"key":"ref163","first-page":"5741","article-title":"Bayesian bits: Unifying quantization and pruning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"van Baalen"},{"key":"ref164","first-page":"22562","article-title":"Fast lossless neural compression with integer-only discrete flows","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00215"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00804"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00637"},{"key":"ref168","first-page":"585","article-title":"Neuron merging: Compensating for pruned neurons","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3018177"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.280"},{"key":"ref171","first-page":"17629","article-title":"Pruning filter in filter","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Meng"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5954"},{"key":"ref173","article-title":"Revisit kernel pruning with lottery regulated grouped convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhong"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195774"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2874634"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3112041"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3162067"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3176809"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_29"},{"key":"ref180","first-page":"6377","article-title":"Pruning neural networks without any data by iteratively conserving synaptic flow","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tanaka"},{"key":"ref181","article-title":"A signal propagation perspective for pruning neural networks at initialization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2906563"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_17"},{"key":"ref184","first-page":"20852","article-title":"The generalization-stability tradeoff in neural network pruning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bartoldson"},{"key":"ref185","article-title":"An entropy-based pruning method for CNN compression","author":"Luo","year":"2017"},{"key":"ref186","first-page":"2925","article-title":"Logarithmic pruning is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Orseau"},{"key":"ref187","article-title":"PROXSGD: Training structured neural networks under regularization and constraints","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang"},{"key":"ref188","first-page":"6382","article-title":"Global sparse momentum SGD for pruning very deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref189","first-page":"29364","article-title":"Heavy tails in SGD and compressibility of overparametrized neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Barsbey"},{"key":"ref190","article-title":"Learning pruning-friendly networks via Frank-Wolfe: One-shot, any-sparsity, and no retraining","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Miao"},{"key":"ref191","article-title":"One-shot pruning of recurrent neural networks by Jacobian spectrum evaluation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref192","first-page":"8557","article-title":"AC\/DC: Alternating compressed\/decompressed training of deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Peste"},{"key":"ref193","article-title":"Layer-adaptive sparsity for the magnitude-based pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref194","first-page":"8557","article-title":"Compressing neural networks: Towards determining the optimal layer-wise decomposition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liebenwein"},{"key":"ref195","first-page":"1051","article-title":"Frequency-domain dynamic pruning for convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/385"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3166101"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3056201"},{"key":"ref199","article-title":"Continual learning via neural pruning","volume-title":"Proc. NeurIPS 2019 Workshop Neuro AI","author":"Golkar"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00021"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00810"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6058"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00478"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3130047"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3027308"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_24"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3085299"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20842"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00333"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01198"},{"key":"ref211","first-page":"28560","article-title":"Revisiting discriminator in GAN compression: A generator-discriminator cooperative compression scheme","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3005574"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00488"},{"key":"ref214","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref215","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref216","article-title":"A generalist agent","author":"Reed","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2864142"},{"key":"ref218","first-page":"27081","article-title":"Scaling up exact neural network compression by RELU stability","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Serra"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_7"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_42"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_37"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.643"},{"key":"ref223","first-page":"2116","article-title":"Model compression with adversarial robustness: A unified optimization framework","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gui"},{"key":"ref224","first-page":"3760","article-title":"Linearity grafting: Relaxed neuron pruning helps certifiable robustness","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref225","first-page":"6575","article-title":"Adversarial neural pruning with latent vulnerability suppression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Madaan"},{"key":"ref226","article-title":"Data-dependent coresets for compressing neural networks with applications to generalization bounds","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baykal"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.478"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00532.x"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-82118-9"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959678"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1561\/2400000003"},{"key":"ref232","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/1978154"},{"key":"ref234","first-page":"1574","article-title":"Stochastic proximal gradient descent with acceleration techniques","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nitanda"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12265"},{"key":"ref236","first-page":"2575","article-title":"Variational dropout and the local reparameterization trick","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kingma"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1097\/ALN.0000000000002350"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1137\/1015034"},{"key":"ref240","first-page":"598","article-title":"Optimal brain damage","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"LeCun"},{"key":"ref241","first-page":"164","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hassibi"},{"key":"ref242","first-page":"2408","article-title":"Optimizing neural networks with kronecker-factored approximate curvature","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Martens"},{"key":"ref243","first-page":"9573","article-title":"Fast approximate natural gradient descent in a kronecker factored eigenbasis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"George"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1214\/06-BA101"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-011-9236-8"},{"key":"ref246","first-page":"2116","article-title":"Dual averaging method for regularized stochastic learning and online optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xiao"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"ref248","article-title":"A tutorial on Bayesian optimization","author":"Frazier","year":"2018"},{"key":"ref249","first-page":"1015","article-title":"Gaussian process optimization in the bandit setting: No regret and experimental design","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Srinivas"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/18.382009"},{"key":"ref251","first-page":"1387","article-title":"Dynamic network surgery for efficient DNNs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1137\/0917055"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139020411"},{"key":"ref254","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref256","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref257","first-page":"1886","article-title":"Channel gating neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hua"},{"key":"ref258","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lillicrap"},{"key":"ref259","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref260","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00189"},{"key":"ref262","first-page":"1683","article-title":"Stochastic gradient Hamiltonian Monte Carlo","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref263","article-title":"An idea based on honey bee swarm for numerical optimization","author":"Karaboga","year":"2005"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.1162\/106365600568086"},{"key":"ref265","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Frankle"},{"key":"ref266","first-page":"3259","article-title":"Linear mode connectivity and the lottery ticket hypothesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Frankle"},{"key":"ref267","article-title":"Snip: Single-shot network pruning based on connection sensitivity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref268","article-title":"Picking winning tickets before training by preserving gradient flow","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref269","first-page":"8580","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jacot"},{"key":"ref270","article-title":"A gradient flow framework for analyzing network pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lubana"},{"key":"ref271","article-title":"Comparing rewinding and fine-tuning in neural network pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Renda"},{"key":"ref272","article-title":"Once-for-all: Train one network and specialize it for efficient deployment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cai"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"ref275","article-title":"Understanding intermediate layers using linear classifier probes","volume-title":"Proc. Int. Conf. Learn. Representations Workshop","author":"Alain"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3256092"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3013541"},{"key":"ref278","article-title":"Dataset pruning: Reducing training data by examining generalization influence","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang"},{"key":"ref279","article-title":"In convolutional nets, there is no such thing as \u201cfully-connected layers","author":"LeCun","year":"2015"},{"key":"ref280","first-page":"240","article-title":"Sparse DNNs with improved adversarial robustness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Guo"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10490207\/10330640.pdf?arnumber=10330640","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:29:35Z","timestamp":1712690975000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10330640\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":280,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3334614","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":[[2024,5]]}}}