{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T21:09:37Z","timestamp":1788728977932,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376695","type":"print"},{"value":"9783032376701","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-37670-1_7","type":"book-chapter","created":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T20:43:53Z","timestamp":1788727433000},"page":"106-120","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Understanding and\u00a0Enhancing Dynamic Sparse Training Through the\u00a0Lens of\u00a0Stochasticity"],"prefix":"10.1007","author":[{"given":"Boqian","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiao","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Senmiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yupeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maurice","family":"van Keulen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mykola","family":"Pechenizkiy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Decebal Constantin","family":"Mocanu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elena","family":"Mocanu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,7]]},"reference":[{"key":"7_CR1","unstructured":"Bellec, G., Kappel, D., Maass, W., Legenstein, R.: Deep rewiring: training very sparse deep networks. In: ICLR 2018 (2018)"},{"key":"7_CR2","unstructured":"Bisla, D., Wang, J., Choromanska, A.: Low-pass filtering SGD for recovering flat optima in the deep learning optimization landscape. In: AISTATS 2022 (2022)"},{"key":"7_CR3","unstructured":"Bottou, L.: Stochastic gradient learning in neural networks. In: Proceedings of Neuro-Nimes (1991)"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Bottou, L.: Large-scale machine learning with stochastic gradient descent. In: Proceedings of COMPSTAT\u20192010, pp. 177\u2013186. Springer (2010)","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"7_CR5","unstructured":"Chen, T., Cheng, Y., Gan, Z., Yuan, L., Zhang, L., Wang, Z.: Chasing sparsity in vision transformers: an end-to-end exploration. In: NeurIPS 2021 (2021)"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR 2009 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"7_CR7","unstructured":"Evci, U., Gale, T., Menick, J., Castro, P.S., Elsen, E.: Rigging the lottery: making all tickets winners. In: ICML 2020 (2020)"},{"key":"7_CR8","unstructured":"Evci, U., Pedregosa, F., Gomez, A., Elsen, E.: The difficulty of training sparse neural networks. arXiv preprint: arXiv:1906.10732 (2019)"},{"key":"7_CR9","unstructured":"Foret, P., Kleiner, A., Mobahi, H., Neyshabur, B.: Sharpness-aware minimization for efficiently improving generalization. In: ICLR 2021 (2021)"},{"key":"7_CR10","unstructured":"Graesser, L., Evci, U., Elsen, E., Castro, P.S.: The state of sparse training in deep reinforcement learning. In: ICML 2022 (2022)"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR 2016 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Ji, J., et al.: A single-step, sharpness-aware minimization is all you need to achieve efficient and accurate sparse training. In: NeurIPS 2024 (2024)","DOI":"10.52202\/079017-1405"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Bottou, L., Orr, G.B., M\u00fcller, K.R.: Efficient backprop. In: Neural Networks: Tricks of the Trade, pp. 9\u201348. Springer (2012)","DOI":"10.1007\/978-3-642-35289-8_3"},{"key":"7_CR14","unstructured":"Lee, J.H., et\u00a0al.: JaxPruner: a concise library for sparsity research. In: Conference on Parsimony and Learning, pp. 515\u2013528. PMLR (2024)"},{"key":"7_CR15","unstructured":"Lee, N., Ajanthan, T., Torr, P.H.S.: Snip: single-shot network pruning based on connection sensitivity. In: ICLR 2019 (2019)"},{"key":"7_CR16","unstructured":"Li, T., et al.: Revisiting random weight perturbation for efficiently improving generalization. Trans. Mach. Learn. Res. 2024 (2024)"},{"key":"7_CR17","unstructured":"Liu, S., et al.: Sparse training via boosting pruning plasticity with neuroregeneration. In: NeurIPS 2021 (2021)"},{"key":"7_CR18","unstructured":"Liu, S., Yin, L., Mocanu, D.C., Pechenizkiy, M.: Do we actually need dense over-parameterization? In-time over-parameterization in sparse training. In: ICML 2021 (2021)"},{"issue":"2\u20133","key":"7_CR19","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/s10994-016-5570-z","volume":"104","author":"DC Mocanu","year":"2016","unstructured":"Mocanu, D.C., Mocanu, E., Nguyen, P.H., Gibescu, M., Liotta, A.: A topological insight into restricted Boltzmann machines. Mach. Learn. 104(2\u20133), 243\u2013270 (2016)","journal-title":"Mach. Learn."},{"issue":"1","key":"7_CR20","doi-asserted-by":"publisher","first-page":"2383","DOI":"10.1038\/s41467-018-04316-3","volume":"9","author":"DC Mocanu","year":"2018","unstructured":"Mocanu, D.C., Mocanu, E., Stone, P., Nguyen, P.H., Gibescu, M., Liotta, A.: Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science. Nat. Commun. 9(1), 2383 (2018)","journal-title":"Nat. Commun."},{"key":"7_CR21","unstructured":"M\u00f6llenhoff, T., Khan, M.E.: SAM as an optimal relaxation of Bayes. In: ICLR 2023 (2023)"},{"key":"7_CR22","unstructured":"Mostafa, H., Wang, X.: Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization. In: ICML 2019 (2019)"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Nowak, A., Grooten, B., Mocanu, D.C., Tabor, J.: Fantastic weights and how to find them: where to prune in dynamic sparse training. NeurIPS 2023 (2023)","DOI":"10.52202\/075280-2409"},{"key":"7_CR24","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR 2015 (2015)"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Sokar, G., Mocanu, D.C., Pechenizkiy, M.: Avoiding forgetting and allowing forward transfer in continual learning via sparse networks. In: ECML PKDD 2022 (2022)","DOI":"10.1007\/978-3-031-26409-2_6"},{"issue":"56","key":"7_CR26","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(56), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR27","unstructured":"Tan, Y., Hu, P., Pan, L., Huang, J., Huang, L.: RLx2: training a sparse deep reinforcement learning model from scratch. In: ICLR 2023 (2023)"},{"key":"7_CR28","unstructured":"Tanaka, H., Kunin, D., Yamins, D.L.K., Ganguli, S.: Pruning neural networks without any data by iteratively conserving synaptic flow. In: NeurIPS 2020 (2020)"},{"key":"7_CR29","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: Meila, M., Zhang, T. (eds.) ICML 2021 (2021)"},{"key":"7_CR30","unstructured":"Wang, C., Zhang, G., Grosse, R.B.: Picking winning tickets before training by preserving gradient flow. In: ICLR 2020 (2020)"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Wu, B., et al.: E2ENet: dynamic sparse feature fusion for accurate and efficient 3D medical image segmentation. In: NeurIPS 2024 (2024)","DOI":"10.52202\/079017-3762"},{"key":"7_CR32","unstructured":"Wu, B., et al.: When data is scarce: scaling sparse language models with repeated training. In: ICML 2026 (2026)"},{"key":"7_CR33","unstructured":"Wu, B., et al.: Dynamic sparse training versus dense training: the unexpected winner in image corruption robustness. In: ICLR 2025 (2025)"},{"key":"7_CR34","unstructured":"Xiao, Q., et al.: Leave it to the specialist: repair sparse LLMs with sparse fine-tuning via sparsity evolution. arXiv preprint: arXiv:2505.24037 (2025)"},{"key":"7_CR35","unstructured":"Xiao, Q., et al.: Memory-efficient LLM training with dynamic sparsity: From stability to practical scaling. In: ICML 2026 (2026)"},{"key":"7_CR36","unstructured":"Yuan, G., et\u00a0al.: MEST: accurate and fast memory-economic sparse training framework on the edge. NeurIPS 2021 (2021)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37670-1_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T20:43:56Z","timestamp":1788727436000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37670-1_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,7]]},"ISBN":["9783032376695","9783032376701"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37670-1_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,7]]},"assertion":[{"value":"7 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Naples","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}