{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T21:52:58Z","timestamp":1774993978741,"version":"3.50.1"},"reference-count":48,"publisher":"MIT Press - Journals","issue":"8","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>This letter develops a novel fixed-time stable neurodynamic flow (FTSNF) implemented in a dynamical system for solving the nonconvex, nonsmooth model L1-\u03b22, \u03b2\u2208[0,1] to recover a sparse signal. FTSNF is composed of many neuron-like elements running in parallel. It is very efficient and has provable fixed-time convergence. First, a closed-form solution of the proximal operator to model L1-\u03b22, \u03b2\u2208[0,1] is presented based on the classic soft thresholding of the L1-norm. Next, the proposed FTSNF is proven to have a fixed-time convergence property without additional assumptions on the convexity and strong monotonicity of the objective functions. In addition, we show that FTSNF can be transformed into other proximal neurodynamic flows that have exponential and finite-time convergence properties. The simulation results of sparse signal recovery verify the effectiveness and superiority of the proposed FTSNF.<\/jats:p>","DOI":"10.1162\/neco_a_01508","type":"journal-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T23:46:24Z","timestamp":1657237584000},"page":"1727-1755","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":6,"title":["Fixed-Time Stable Neurodynamic Flow to Sparse Signal Recovery via Nonconvex L1-\u03b22-Norm"],"prefix":"10.1162","volume":"34","author":[{"given":"You","family":"Zhao","sequence":"first","affiliation":[{"name":"Key Laboratory of Dependable Services Computing in Cyber Physical Society-Ministry of Education, College of Computer Science, Chongqing University, Chongqing 400044, China Zhaoyou1991sdtz@163.com"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofeng","family":"Liao","sequence":"additional","affiliation":[{"name":"IEEE Fellow, and Key Laboratory of Dependable Services Computing in Cyber Physical Society-Ministry of Education, College of Computer Science, Chongqing University, Chongqing 400044, China xfliao@cqu.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"He","sequence":"additional","affiliation":[{"name":"Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing, College of Electronics and Information Engineering, Southwest University, Chongqing 400715, China hexingdoc@swu.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","published-online":{"date-parts":[[2022,7,14]]},"reference":[{"issue":"3","key":"2022071522333305500_B1","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1109\/TIP.2010.2076294","article-title":"An augmented Lagrangian approach to the constrained optimization formulation of imaging inverse problems","volume":"20","author":"Afonso","year":"2010","journal-title":"IEEE Transactions on Image Processing"},{"key":"2022071522333305500_B2","article-title":"Sparse coding and dictionary learning for image analysis","volume-title":"Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition","author":"Bach","year":"2010"},{"issue":"17","key":"2022071522333305500_B3","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2271482","article-title":"Convergence speed of a dynamical system for sparse recovery","volume":"61","author":"Balavoine","year":"2013","journal-title":"IEEE Transactions on Signal Processing"},{"issue":"3","key":"2022071522333305500_B4","doi-asserted-by":"crossref","DOI":"10.1109\/TNNLS.2013.2278427","article-title":"Smoothing neural network for constrained non-Lipschitz optimization with applications","volume":"23","author":"Bian","year":"2012","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"1","key":"2022071522333305500_B5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000016","article-title":"Distributed optimization and statistical learning via the alternating direction method of multipliers","volume":"3","author":"Boyd","year":"2011","journal-title":"Foundations and Trends in Machine Learning"},{"issue":"9\u201310","key":"2022071522333305500_B6","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1016\/j.crma.2008.03.014","article-title":"The restricted isometry property and its implications for compressed sensing","volume":"346","author":"Cand\u00e8s","year":"2008","journal-title":"Comptes rendus mathematique"},{"issue":"8","key":"2022071522333305500_B7","doi-asserted-by":"crossref","first-page":"1207","DOI":"10.1002\/cpa.20124","article-title":"Stable signal recovery from incomplete and inaccurate measurements","volume":"59","author":"Cand\u00e8s","year":"2006","journal-title":"Communications on Pure and Applied Mathematic"},{"issue":"10","key":"2022071522333305500_B8","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1109\/LSP.2007.898300","article-title":"Exact reconstruction of sparse signals via nonconvex minimization","volume":"14","author":"Chartrand","year":"2007","journal-title":"IEEE Signal Processing Letters"},{"issue":"12","key":"2022071522333305500_B9","doi-asserted-by":"publisher","first-page":"2271","DOI":"10.1109\/TMI.2014.2336860","article-title":"Artifact suppressed dictionary learning for low-dose CT image processing","volume":"33","author":"Chen","year":"2014","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"456","key":"2022071522333305500_B10","doi-asserted-by":"publisher","first-page":"1348","DOI":"10.1198\/016214501753382273","article-title":"Variable selection via nonconcave penalized likelihood and its oracle properties","volume":"96","author":"Fan","year":"2001","journal-title":"Journal of the American Statistical Association"},{"issue":"10","key":"2022071522333305500_B11","doi-asserted-by":"publisher","first-page":"2395","DOI":"10.1109\/TNNLS.2016.2575860","article-title":"Lagrange programming neural network for non-differentiable optimization problems in sparse approximation","volume":"28","author":"Feng","year":"2017","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2022071522333305500_B12","doi-asserted-by":"publisher","first-page":"1760","DOI":"10.1109\/LSP.2020.3027490","article-title":"CAPPA: Continuous-time accelerated proximal point algorithm for sparse recovery","volume":"27","author":"Garg","year":"2020","journal-title":"IEEE Signal Processing Letters"},{"key":"2022071522333305500_B13","author":"Garg","year":"2019","journal-title":"Fixed-time stable proximal dynamical system for solving mixed variational inequality problems."},{"issue":"5","key":"2022071522333305500_B14","doi-asserted-by":"publisher","first-page":"2002","DOI":"10.1109\/TAC.2020.3001436","article-title":"Fixed-time stable gradient flows: Applications to continuous-time optimization","volume":"66","author":"Garg","year":"2021","journal-title":"IEEE Transactions on Automatic Control"},{"key":"2022071522333305500_B15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3088535","article-title":"A fixed-time projection neural network for solving l1-minimization problem","volume-title":"IEEE Transactions on Neural Networks and Learning Systems","author":"He","year":"2021"},{"key":"2022071522333305500_B16","first-page":"609","volume-title":"Advances in neural information processing systems","author":"Huang","year":"2006"},{"issue":"2","key":"2022071522333305500_B17","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1137\/110840364","article-title":"Improved iteratively reweighted least squares for unconstrained smoothed lq minimization","volume":"51","author":"Lai","year":"2013","journal-title":"SIAM Journal on Numerical Analysis"},{"issue":"1","key":"2022071522333305500_B18","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1109\/TSG.2016.2521377","article-title":"Efficient computation for sparse load shifting in demand side management","volume":"8","author":"Li","year":"2016","journal-title":"IEEE Transactions on Smart Grid"},{"key":"2022071522333305500_B19","doi-asserted-by":"crossref","first-page":"8201","DOI":"10.1109\/IECON.2017.8217439","article-title":"A fixed time distributed optimization: A sliding mode perspective","volume-title":"Proceedings of the IECON 2017-43rd Annual Conference of the IEEE Industrial Electronics Society","author":"Li","year":"2017"},{"issue":"8","key":"2022071522333305500_B20","doi-asserted-by":"publisher","first-page":"1531","DOI":"10.1162\/neco_a_01294","article-title":"A discrete-time neurodynamic approach to sparsity-constrained nonnegative matrix factorization","volume":"32","author":"Li","year":"2020","journal-title":"Neural Computation"},{"issue":"2","key":"2022071522333305500_B21","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1109\/TNN.2005.863424","article-title":"Blind estimation of channel parameters and source components for EEG signals: A sparse factorization approach","volume":"17","author":"Li","year":"2006","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"16","key":"2022071522333305500_B22","doi-asserted-by":"publisher","first-page":"11323","DOI":"10.1016\/j.jfranklin.2019.06.024","article-title":"Predefined-time optimization for distributed resource allocation","volume":"357","author":"Lin","year":"2020","journal-title":"Journal of the Franklin Institute"},{"issue":"2","key":"2022071522333305500_B23","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1162\/NECO_a_00922","article-title":"Multistability of delayed recurrent neural networks with Mexican hat activation functions","volume":"29","author":"Liu","year":"2017","journal-title":"Neural Computation"},{"issue":"11","key":"2022071522333305500_B24","doi-asserted-by":"publisher","first-page":"2962","DOI":"10.1162\/NECO_a_00029","article-title":"A novel recurrent neural network with finite-time convergence for linear programming","volume":"22","author":"Liu","year":"2010","journal-title":"Neural Computation"},{"issue":"5","key":"2022071522333305500_B25","doi-asserted-by":"publisher","first-page":"1366","DOI":"10.1162\/neco.2007.03-07-488","article-title":"A one-layer recurrent neural network with a discontinuous activation function for linear programming","volume":"20","author":"Liu","year":"2008","journal-title":"Neural Computation"},{"issue":"3","key":"2022071522333305500_B26","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1109\/TNNLS.2015.2481006","article-title":"L1-minimization algorithms for sparse signal reconstruction based on a projection neural network","volume":"27","author":"Liu","year":"2016","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"3","key":"2022071522333305500_B27","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1007\/s10589-017-9900-2","article-title":"Further properties of the forward-backward envelope with applications to difference-of-convex programming","volume":"67","author":"Liu","year":"2017","journal-title":"Computational Optimization and Applications"},{"issue":"2","key":"2022071522333305500_B28","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1007\/s10915-017-0463-2","article-title":"Fast L1-L2 minimization via a proximal operator","volume":"74","author":"Lou","year":"2018","journal-title":"Journal of Scientific Computing"},{"issue":"3","key":"2022071522333305500_B29","doi-asserted-by":"publisher","first-page":"1082","DOI":"10.1007\/s10915-016-0169-x","article-title":"Point source super-resolution via non-convex l1 based methods","volume":"68","author":"Lou","year":"2016","journal-title":"Journal of Scientific Computing"},{"issue":"8","key":"2022071522333305500_B30","doi-asserted-by":"publisher","first-page":"2106","DOI":"10.1109\/TAC.2011.2179869","article-title":"Nonlinear feedback design for fixed-time stabilization of linear control systems","volume":"57","author":"Polyakov","year":"2012","journal-title":"IEEE Transactions on Automatic Control"},{"key":"2022071522333305500_B31","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1109\/IEEECONF44664.2019.9048830","article-title":"L1-2 regularized logistic regression","volume-title":"Proceedings of the 2019 53rd Asilomar Conference on Signals, Systems, and Computers","author":"Qin","year":"2019"},{"key":"2022071522333305500_B32","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.sigpro.2019.04.010","article-title":"Dynamical sparse signal recovery with fixed-time convergence","volume":"162","author":"Ren","year":"2019","journal-title":"Signal Processing"},{"key":"2022071522333305500_B33","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.1162\/neco.2008.03-07-486","article-title":"Sparse coding via thresholding and local competition in neural circuits","volume":"20","author":"Rozell","year":"2008","journal-title":"Neural Computation"},{"issue":"12","key":"2022071522333305500_B34","doi-asserted-by":"publisher","first-page":"1067","DOI":"10.1109\/LSP.2009.2030111","article-title":"Dual-augmented Lagrangian method for efficient sparse reconstruction","volume":"16","author":"Tomioka","year":"2009","journal-title":"IEEE Signal Processing Letters"},{"issue":"2","key":"2022071522333305500_B35","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1109\/TPAMI.2011.112","article-title":"Toward a practical face recognition system: Robust alignment and illumination by sparse representation","volume":"34","author":"Wagner","year":"2011","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"11","key":"2022071522333305500_B36","doi-asserted-by":"publisher","first-page":"4326","DOI":"10.1007\/s00034-017-0532-7","article-title":"Generalized sparse recovery model and its neural dynamical optimization method for compressed sensing","volume":"36","author":"Wang","year":"2017","journal-title":"Circuits, Systems, and Signal Processing"},{"key":"2022071522333305500_B37","doi-asserted-by":"publisher","first-page":"6058","DOI":"10.1007\/s00034-020-01445-3","article-title":"A neurodynamic algorithm for sparse signal reconstruction with finite-time convergence","volume":"39","author":"Wen","year":"2020","journal-title":"Circuits, Systems, and Signal Processing"},{"key":"2022071522333305500_B38","doi-asserted-by":"publisher","first-page":"1031","DOI":"10.1109\/JPROC.2010.2044470","article-title":"Sparse representation for computer vision and pattern recognition","volume":"98","author":"Wright","year":"2010","journal-title":"Proceedings of the IEEE"},{"issue":"3","key":"2022071522333305500_B39","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s10915-015-0094-4","article-title":"A Barzilai-Borwein-like iterative half thresholding algorithm for the l1\/2 regularized problem","volume":"67","author":"Wu","year":"2016","journal-title":"Journal of Scientific Computing"},{"issue":"1","key":"2022071522333305500_B40","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1109\/TNNLS.2018.2836933","article-title":"A discrete-time projection neural network for sparse signal reconstruction with application to face recognition","volume":"30","author":"Xu","year":"2019","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"7","key":"2022071522333305500_B41","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1109\/TNNLS.2012.2197412","article-title":"L1\/2 regularization: A thresholding representation theory and a fast solver","volume":"23","author":"Xu","year":"2012","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"1","key":"2022071522333305500_B42","doi-asserted-by":"publisher","first-page":"A536","DOI":"10.1137\/140952363","article-title":"Minimization of l1-l2 for compressed sensing","volume":"37","author":"Yin","year":"2015","journal-title":"SIAM Journal on Scientific Computing"},{"issue":"23","key":"2022071522333305500_B43","doi-asserted-by":"publisher","first-page":"6146","DOI":"10.1109\/TSP.2017.2745468","article-title":"Dynamical sparse recovery with finite-time convergence","volume":"65","author":"Yu","year":"2017","journal-title":"IEEE Transactions on Signal Processing"},{"issue":"1","key":"2022071522333305500_B44","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1007\/s10107-018-1236-x","article-title":"Minimization of transformed l1 penalty: Theory, difference of convex function algorithm, and robust application in compressed sensing","volume":"169","author":"Zhang","year":"2018","journal-title":"Mathematical Programming"},{"key":"2022071522333305500_B45","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.neunet.2017.12.008","article-title":"Smoothing inertial projection neural network for minimization lp-q in sparse signal reconstruction","volume":"99","author":"Zhao","year":"2018","journal-title":"Neural Networks"},{"key":"2022071522333305500_B46","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.neunet.2021.02.006","article-title":"Smoothing inertial neurodynamic approach for sparse signal reconstruction via lp-norm minimization","volume":"140","author":"Zhao","year":"2021","journal-title":"Neural Networks"},{"key":"2022071522333305500_B47","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.neucom.2018.06.050","article-title":"An inertial projection neural network for sparse signal reconstruction via l1-2 minimization","volume":"315","author":"Zhu","year":"2018","journal-title":"Neurocomputing"},{"key":"2022071522333305500_B48","first-page":"217","article-title":"A generalized iterated shrinkage algorithm for non-convex sparse coding","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Zuo","year":"2013"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/34\/8\/1727\/2034959\/neco_a_01508.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/34\/8\/1727\/2034959\/neco_a_01508.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T22:33:53Z","timestamp":1657924433000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/34\/8\/1727\/111779\/Fixed-Time-Stable-Neurodynamic-Flow-to-Sparse"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,14]]},"references-count":48,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2022,7,14]]},"published-print":{"date-parts":[[2022,7,14]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01508","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,8]]},"published":{"date-parts":[[2022,7,14]]}}}