{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T08:28:03Z","timestamp":1793608083437,"version":"4.5.0"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]},{"DOI":"10.13039\/501100009731","name":"Sichuan Youth Foundation for Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,2]]},"DOI":"10.1016\/j.neunet.2026.109725","type":"journal-article","created":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T06:48:08Z","timestamp":1791442088000},"page":"109725","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Adaptive parameter manifold learning for low-dimensional neural network optimization"],"prefix":"10.1016","volume":"206","author":[{"given":"Zhekai","family":"Du","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Ao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jieyan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bei","family":"Hui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109725_bib0001","series-title":"International conference on machine learning","first-page":"233","article-title":"A closer look at memorization in deep networks","author":"Arpit","year":"2017"},{"key":"10.1016\/j.neunet.2026.109725_bib0002","series-title":"Proceedings of the 60th annual meeting of the association for computational linguistics (volume 2: Short papers)","first-page":"1","article-title":"BitFit: Simple parameter-efficient fine-tuning for transformer-based masked language-models","author":"Ben Zaken","year":"2022"},{"key":"10.1016\/j.neunet.2026.109725_bib0003","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109725_bib0004","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"3606","article-title":"Describing textures in the wild","author":"Cimpoi","year":"2014"},{"key":"10.1016\/j.neunet.2026.109725_bib0005","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1109\/OJCSYS.2023.3315088","article-title":"Low-rank gradient descent","volume":"2","author":"Cosson","year":"2023","journal-title":"IEEE Open Journal of Control Systems"},{"key":"10.1016\/j.neunet.2026.109725_bib0006","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TAI.2026.3664343","article-title":"Momentum-based zeroth-order gradient method for distributed black-box optimization","volume":"7","author":"Dang","year":"2026","journal-title":"IEEE Transactions on Artificial Intelligence"},{"issue":"1","key":"10.1016\/j.neunet.2026.109725_bib0007","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1109\/TEVC.2025.3541046","article-title":"Data-driven evolutionary algorithm based on inductive graph neural networks for multimodal multiobjective optimization","volume":"30","author":"Dang","year":"2026","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"10.1016\/j.neunet.2026.109725_bib0008","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TETCI.2024.3397996","article-title":"A generative adversarial networks model based evolutionary algorithm for multimodal multi-objective optimization","author":"Dang","year":"2024","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"issue":"1","key":"10.1016\/j.neunet.2026.109725_bib0009","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1109\/MCI.2024.3486284","article-title":"Transformer-based intelligent prediction model for multimodal multi-objective optimization","volume":"20","author":"Dang","year":"2025","journal-title":"IEEE Computational Intelligence Magazine"},{"key":"10.1016\/j.neunet.2026.109725_bib0010","doi-asserted-by":"crossref","first-page":"10088","DOI":"10.52202\/075280-0441","article-title":"Qlora: Efficient finetuning of quantized llms","volume":"36","author":"Dettmers","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109725_bib0011","series-title":"International conference on learning representations","article-title":"An image is worth 16\u202f\u00d7\u202f16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.neunet.2026.109725_bib0012","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.ins.2015.09.021","article-title":"Approximation with random bases: Pro et contra","volume":"364","author":"Gorban","year":"2016","journal-title":"Information Sciences"},{"issue":"5","key":"10.1016\/j.neunet.2026.109725_bib0013","doi-asserted-by":"crossref","first-page":"3043","DOI":"10.4249\/scholarpedia.3043","article-title":"Grassberger-procaccia algorithm","volume":"2","author":"Grassberger","year":"2007","journal-title":"Scholarpedia"},{"key":"10.1016\/j.neunet.2026.109725_bib0014","first-page":"12140","article-title":"Improving neural network training in low dimensional random bases","volume":"33","author":"Gressmann","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109725_bib0015","unstructured":"Gur-Ari, G., Roberts, D. A., & Dyer, E. (2018). Gradient descent happens in a tiny subspace. arXiv: 1812.04754."},{"key":"10.1016\/j.neunet.2026.109725_bib0016","first-page":"8527","article-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","volume":"31","author":"Han","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109725_bib0017","series-title":"International conference on learning representations","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han","year":"2016"},{"key":"10.1016\/j.neunet.2026.109725_bib0018","series-title":"International conference on learning representations","article-title":"Towards a unified view of parameter-efficient transfer learning","author":"He","year":"2022"},{"key":"10.1016\/j.neunet.2026.109725_bib0019","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2026.109725_bib0020","series-title":"Nips deep learning and representation learning workshop","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"10.1016\/j.neunet.2026.109725_bib0021","series-title":"International conference on learning representations","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109725_bib0022","series-title":"Proceedings of the 2023 conference on empirical methods in natural language processing","first-page":"5254","article-title":"LLM-adapters: An adapter family for parameter-efficient fine-tuning of large language models","author":"Hu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109725_bib0023","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"2704","article-title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference","author":"Jacob","year":"2018"},{"key":"10.1016\/j.neunet.2026.109725_bib0024","series-title":"International conference on machine learning","first-page":"4804","article-title":"Beyond synthetic noise: Deep learning on controlled noisy labels","author":"Jiang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109725_bib0025","unstructured":"Kozak, D., Becker, S., Doostan, A., & Tenorio, L. (2019). Stochastic subspace descent. arXiv: 1904.01145."},{"key":"10.1016\/j.neunet.2026.109725_bib0026","series-title":"Proceedings of the IEEE international conference on computer vision workshops","first-page":"554","article-title":"3D object representations for fine-grained categorization","author":"Krause","year":"2013"},{"key":"10.1016\/j.neunet.2026.109725_bib0027","series-title":"International conference on learning representations","article-title":"Measuring the intrinsic dimension of objective landscapes","author":"Li","year":"2018"},{"key":"10.1016\/j.neunet.2026.109725_bib0028","series-title":"Proceedings of machine learning and systems","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Li","year":"2020"},{"issue":"3","key":"10.1016\/j.neunet.2026.109725_bib0029","first-page":"3411","article-title":"Low dimensional trajectory hypothesis is true: DNNs can be trained in tiny subspaces","volume":"45","author":"Li","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109725_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106113","article-title":"Contrastive learning of graphs under label noise","volume":"172","author":"Li","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109725_bib0031","series-title":"Forty-first international conference on machine learning","article-title":"Dora: Weight-decomposed low-rank adaptation","author":"Liu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109725_bib0032","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv: 1907.11692."},{"key":"10.1016\/j.neunet.2026.109725_bib0033","series-title":"Proceedings of the 32nd ACM international conference on information and knowledge management","first-page":"1667","article-title":"Exploring low-dimensional manifolds of deep neural network parameters for improved model optimization","author":"Lu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109725_bib0034","series-title":"Artificial intelligence and statistics","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"key":"10.1016\/j.neunet.2026.109725_bib0035","series-title":"2012 IEEE conference on computer vision and pattern recognition","first-page":"3498","article-title":"Cats and dogs","author":"Parkhi","year":"2012"},{"key":"10.1016\/j.neunet.2026.109725_bib0036","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107501","article-title":"Federated learning with randomized alternating direction method of multipliers and application in training neural networks","volume":"189","author":"Phan","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109725_bib0037","series-title":"International conference on learning representations","article-title":"Does SGD really happen in tiny subspaces?","author":"Song","year":"2025"},{"key":"10.1016\/j.neunet.2026.109725_bib0038","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109725_bib0039","series-title":"Proceedings of the 2018\u202fEMNLP workshop blackboxNLP: Analyzing and interpreting neural networks for NLP","first-page":"353","article-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","author":"Wang","year":"2018"},{"key":"10.1016\/j.neunet.2026.109725_bib0040","series-title":"Proceedings of the 2021 conference on empirical methods in natural language processing","first-page":"9514","article-title":"Raise a child in large language model: Towards effective and generalizable fine-tuning","author":"Xu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109725_bib0041","series-title":"Proceedings of the 29th ACM international conference on information & knowledge management","first-page":"2893","article-title":"Query-aware tip generation for vertical search","author":"Yang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109725_bib0042","series-title":"International conference on learning representations","article-title":"Understanding deep learning requires rethinking generalization","author":"Zhang","year":"2017"},{"key":"10.1016\/j.neunet.2026.109725_bib0043","series-title":"International conference on learning representations","article-title":"AdaLoRA: Adaptive budget allocation for parameter-efficient fine-tuning","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109725_bib0044","series-title":"Proceedings of the 58th annual meeting of the association for computational linguistics: System demonstrations","first-page":"270","article-title":"DIALOGPT: Large-scale generative pre-training for conversational response generation","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109725_bib0045","series-title":"International conference on intelligent data engineering and automated learning","first-page":"477","article-title":"Nonlinear dimension reduction via local tangent space alignment","author":"Zhang","year":"2003"},{"key":"10.1016\/j.neunet.2026.109725_bib0046","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106810","article-title":"Fractional-order stochastic gradient descent method with momentum and energy for deep neural networks","volume":"181","author":"Zhou","year":"2025","journal-title":"Neural Networks"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011809?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011809?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T07:50:02Z","timestamp":1793605802000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026011809"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,2]]},"references-count":46,"alternative-id":["S0893608026011809"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109725","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Adaptive parameter manifold learning for low-dimensional neural network optimization","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109725","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109725"}}