{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:32:19Z","timestamp":1760059939107,"version":"build-2065373602"},"reference-count":25,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T00:00:00Z","timestamp":1752969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Social Science Fund of China","award":["1246010681"],"award-info":[{"award-number":["1246010681"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>This paper proposes a Distributed Adaptive Regularization Algorithm (DARN) for solving composite non-convex and non-smooth optimization problems in multi-agent systems. The algorithm employs a three-phase iterative framework to achieve efficient collaborative optimization: (1) a local regularized optimization step, which utilizes proximal mappings to enforce strong convexity of weakly convex objectives and ensure subproblem well-posedness; (2) a consensus update based on doubly stochastic matrices, guaranteeing asymptotic convergence of agent states to a global consensus point; and (3) an innovative adaptive regularization mechanism that dynamically adjusts regularization strength using local function value variations to balance stability and convergence speed. Theoretical analysis demonstrates that the algorithm maintains strict monotonic descent under non-convex and non-smooth conditions by constructing a mixed time-scale Lyapunov function, achieving a sublinear convergence rate. Notably, we prove that the projection-based update rule for regularization parameters preserves lower-bound constraints, while spectral decay properties of consensus errors and perturbations from local updates are globally governed by the Lyapunov function. Numerical experiments validate the algorithm\u2019s superiority in sparse principal component analysis and robust matrix completion tasks, showing a 6.6% improvement in convergence speed and a 51.7% reduction in consensus error compared to fixed-regularization methods. This work provides theoretical guarantees and an efficient framework for distributed non-convex optimization in heterogeneous networks.<\/jats:p>","DOI":"10.3390\/sym17071159","type":"journal-article","created":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T07:56:14Z","timestamp":1753084574000},"page":"1159","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DARN: Distributed Adaptive Regularized Optimization with Consensus for Non-Convex Non-Smooth Composite Problems"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0272-1210","authenticated-orcid":false,"given":"Cunlin","family":"Li","sequence":"first","affiliation":[{"name":"School of Mathematics and Information Science, Northern Minzu University, Yinchuan 750021, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6713-4000","authenticated-orcid":false,"given":"Yinpu","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Mathematics and Information Science, Northern Minzu University, Yinchuan 750021, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"3165","DOI":"10.1109\/TAC.2021.3095456","article-title":"Distributed aggregative optimization over multi-agent networks","volume":"67","author":"Li","year":"2021","journal-title":"IEEE Trans. Autom. Control"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1016\/j.arcontrol.2019.05.006","article-title":"A survey of distributed optimization","volume":"47","author":"Yang","year":"2019","journal-title":"Annu. Rev. Control"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1146\/annurev-control-060117-105131","article-title":"Distributed optimization for control","volume":"1","author":"Liu","year":"2018","journal-title":"Annu. Rev. Control Robot. Auton. Syst."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"6013","DOI":"10.1109\/TSP.2015.2461520","article-title":"A proximal gradient algorithm for decentralized composite optimization","volume":"63","author":"Shi","year":"2015","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4494","DOI":"10.1109\/TSP.2019.2926022","article-title":"A decentralized proximal-gradient method with network independent step-sizes and separated convergence rates","volume":"67","author":"Li","year":"2019","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1080\/02331934.2020.1800699","article-title":"A proximal gradient splitting method for solving convex vector optimization problems","volume":"71","author":"Melo","year":"2022","journal-title":"Optimization"},{"key":"ref_7","first-page":"1","article-title":"Accelerating adaptive cubic regularization of Newton\u2019s method via random sampling","volume":"23","author":"Chen","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref_8","first-page":"5331","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","volume":"30","author":"Lian","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.1109\/TCNS.2022.3213706","article-title":"Distributed proximal gradient algorithm for nonconvex optimization over time-varying networks","volume":"10","author":"Jiang","year":"2022","journal-title":"IEEE Trans. Control Netw. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"5230","DOI":"10.1109\/TAC.2022.3216965","article-title":"Distributed robust optimization for networked agent systems with unknown nonlinearities","volume":"68","author":"Wen","year":"2022","journal-title":"IEEE Trans. Autom. Control"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"5154","DOI":"10.1109\/TAC.2023.3347328","article-title":"Distributed constrained optimization over unbalanced time-varying digraphs: A randomized constraint solving algorithm","volume":"69","author":"Luan","year":"2023","journal-title":"IEEE Trans. Autom. Control"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1255","DOI":"10.1007\/s10957-024-02386-6","article-title":"On the Relationship Between the Kurdyka\u2013\u0141ojasiewicz Property and Error Bounds on Hadamard Manifolds","volume":"200","author":"Melo","year":"2024","journal-title":"J. Optim. Theory Appl."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Duchi, J.C., Agarwal, A., and Wainwright, M.J. (2012, January 1\u20135). Dual averaging for distributed optimization. Proceedings of the 2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton), Monticello, IL, USA.","DOI":"10.1109\/Allerton.2012.6483406"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2597","DOI":"10.1137\/16M1084316","article-title":"Achieving geometric convergence for distributed optimization over time-varying graphs","volume":"27","author":"Nedic","year":"2017","journal-title":"SIAM J. Optim."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1287\/moor.2017.0889","article-title":"Error bounds, quadratic growth, and linear convergence of proximal methods","volume":"43","author":"Drusvyatskiy","year":"2018","journal-title":"Math. Oper. Res."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Kanzow, C., and Lehmann, L. (2024). Convergence of Nonmonotone Proximal Gradient Methods under the Kurdyka-Lojasiewicz Property without a Global Lipschitz Assumption. arXiv.","DOI":"10.1007\/s10957-025-02762-w"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1007\/s10915-022-01815-w","article-title":"Moreau envelope augmented Lagrangian method for nonconvex optimization with linear constraints","volume":"91","author":"Zeng","year":"2022","journal-title":"J. Sci. Comput."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2291","DOI":"10.3934\/dcdsb.2015.20.2291","article-title":"Review on computational methods for Lyapunov functions","volume":"20","author":"Giesl","year":"2015","journal-title":"Discret. Contin. Dyn. Syst. B"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2508","DOI":"10.1109\/TIT.2006.874516","article-title":"Randomized gossip algorithms","volume":"52","author":"Boyd","year":"2006","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Bauschke, H.H., Combettes, P.L., and Bauschke, H.H. (2017). Correction to: Convex Analysis and Monotone Operator Theory in Hilbert Spaces, Springer International Publishing.","DOI":"10.1007\/978-3-319-48311-5"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"4327","DOI":"10.1109\/TAC.2020.3034212","article-title":"Distributed asynchronous consensus control for nonlinear multiagent systems under switching topologies","volume":"66","author":"Li","year":"2020","journal-title":"IEEE Trans. Autom. Control"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhang, S., and Bailey, C.P. (2021, January 29\u201331). A Primal-Dual Algorithm for Distributed Sparse Principal Component Analysis. Proceedings of the 2021 IEEE International Conference on Data Science and Computer Application (ICDSCA), Dalian, China.","DOI":"10.1109\/ICDSCA53499.2021.9650142"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Abbasi, A.A., and Vaswani, N. (2024). Efficient Federated Low Rank Matrix Completion. arXiv.","DOI":"10.1109\/Allerton58177.2023.10313472"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"5850","DOI":"10.1109\/TSP.2019.2946020","article-title":"Distributed gradient descent algorithm robust to an arbitrary number of byzantine attackers","volume":"67","author":"Cao","year":"2019","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1137\/080716542","article-title":"A fast iterative shrinkage-thresholding algorithm for linear inverse problems","volume":"2","author":"Beck","year":"2009","journal-title":"SIAM J. Imaging Sci."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/7\/1159\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:12:57Z","timestamp":1760033577000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/7\/1159"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":25,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["sym17071159"],"URL":"https:\/\/doi.org\/10.3390\/sym17071159","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2025,7,20]]}}}