{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:51:32Z","timestamp":1791489092163,"version":"4.3.4"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"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":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1109\/tpami.2026.3722118","type":"journal-article","created":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T19:06:34Z","timestamp":1786388794000},"page":"15054-15066","source":"Crossref","is-referenced-by-count":0,"title":["Random Sparse Networks Training With Sharpness-Aware Regularization"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6023-6064","authenticated-orcid":false,"given":"Yue","family":"Bai","sequence":"first","affiliation":[{"name":"Northeastern University","place":["Boston, MA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0825-8371","authenticated-orcid":false,"given":"Mingyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northeastern University","place":["Boston, MA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6951-901X","authenticated-orcid":false,"given":"Huan","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University","place":["Boston, MA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5639-7540","authenticated-orcid":false,"given":"Zhiqiang","family":"Tao","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology","place":["Rochester, NY, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kunpeng","family":"Li","sequence":"additional","affiliation":[{"name":"Meta Generative AI","place":["Menlo Park, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizhou","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University","place":["Boston, MA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Fu","sequence":"additional","affiliation":[{"name":"Northeastern University","place":["Boston, MA, USA"],"department":["Department of Electrical and Computer Engineering, and Khoury College of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref2","first-page":"322","article-title":"Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arora"},{"key":"ref3","article-title":"Fast convergence of natural gradient descent for overparameterized neural networks","author":"Zhang","year":"2019"},{"key":"ref4","article-title":"Picking winning tickets before training by preserving gradient flow","author":"Wang","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2017.2765695"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"ref7","article-title":"The state of sparsity in deep neural networks","author":"Gale","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref9","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han","year":"2015"},{"key":"ref10","article-title":"Learning both weights and connections for efficient neural networks","author":"Han","year":"2015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref12","first-page":"598","article-title":"Optimal brain damage","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"LeCun"},{"key":"ref13","volume-title":"Second Order Derivatives for Network Pruning: Optimal Brain Surgeon","author":"Hassibi","year":"1993"},{"key":"ref14","first-page":"6566","article-title":"EigenDamage: Structured pruning in the kronecker-factored eigenbasis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref15","article-title":"WoodFisher: Efficient second-order approximations for model compression","author":"Singh","year":"2020"},{"key":"ref16","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","author":"Lee","year":"2018"},{"key":"ref17","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"Frankle","year":"2018"},{"key":"ref18","article-title":"Sharpness-aware minimization for efficiently improving generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Foret"},{"key":"ref19","article-title":"Dual lottery ticket hypothesis","author":"Bai","year":"2022"},{"key":"ref20","article-title":"Learning sparse neural networks through $ l\\_{0}$l_0 regularization","author":"Louizos","year":"2017"},{"key":"ref21","article-title":"Rethinking the smaller-norm-less-informative assumption in channel pruning of convolution layers","author":"Ye","year":"2018"},{"key":"ref22","article-title":"Neural pruning via growing regularization","author":"Wang","year":"2020"},{"key":"ref23","article-title":"Generalized dropout","author":"Srinivas","year":"2016"},{"key":"ref24","article-title":"Learning efficient image super-resolution networks via structure-regularized pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref25","first-page":"2695","article-title":"Aligned structured sparsity learning for efficient image super-resolution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268675"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01157"},{"key":"ref28","article-title":"A signal propagation perspective for pruning neural networks at initialization","author":"Lee","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/786"},{"key":"ref30","article-title":"Drawing early-bird tickets: Toward more efficient training of deep networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"You"},{"key":"ref31","article-title":"The unreasonable effectiveness of random pruning: Return of the most naive baseline for sparse training","author":"Liu","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-04316-3"},{"key":"ref33","first-page":"4646","article-title":"Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mostafa"},{"key":"ref34","article-title":"Sparse networks from scratch: Faster training without losing performance","author":"Dettmers","year":"2019"},{"key":"ref35","article-title":"Deep rewiring: Training very sparse deep networks","author":"Bellec","year":"2017"},{"key":"ref36","article-title":"Rigging the lottery: Making all tickets winners","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Evci"},{"key":"ref37","article-title":"Trainability preserving neural pruning","author":"Wang","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2736"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852463"},{"key":"ref40","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"Foret","year":"2020"},{"key":"ref41","article-title":"Pruning filters for efficient ConvNets","author":"Li","year":"2016"},{"key":"ref42","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref46","article-title":"SparseGPT: Massive language models can be accurately pruned in one-shot","author":"Frantar","year":"2023"},{"key":"ref47","article-title":"A simple and effective pruning approach for large language models","author":"Sun","year":"2023"},{"key":"ref48","article-title":"Outlier weighed layerwise sparsity (OWL): A missing secret sauce for pruning LLMs to high sparsity","author":"Yin","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0742"},{"key":"ref50","article-title":"Boosting large language models with mask fine-tuning","author":"Zhang","year":"2026"},{"key":"ref51","article-title":"Rethinking fine-tuning: Unlocking hidden capabilities in vision-language models","author":"Zhang","year":"2025"},{"key":"ref52","article-title":"Program synthesis with large language models","author":"Austin","year":"2021"},{"key":"ref53","article-title":"DeepSeek-coder: When the large language model meets programming\u2013The rise of code intelligence","author":"Guo","year":"2024"},{"key":"ref54","article-title":"Keep the gradients flowing: Using gradient flow to study sparse network optimization","author":"Tessera","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20611"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11723300\/11646482.pdf?arnumber=11646482","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:09:09Z","timestamp":1791486549000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11646482\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":55,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3722118","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":[[2026,11]]}}}