{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T15:46:05Z","timestamp":1753890365394,"version":"3.41.2"},"reference-count":27,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T00:00:00Z","timestamp":1669075200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11971480","61977065"],"award-info":[{"award-number":["11971480","61977065"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Appl. Math. Stat."],"abstract":"<jats:p>In this paper, we propose a new algorithm called ModelBI by blending the Bregman iterative regularization method and the model function technique for solving a class of nonconvex nonsmooth optimization problems. On one hand, we use the model function technique, which is essentially a first-order approximation to the objective function, to go beyond the traditional Lipschitz gradient continuity. On the other hand, we use the Bregman iterative regularization to generate solutions fitting certain structures. Theoretically, we show the global convergence of the proposed algorithm with the help of the Kurdyka-\u0141ojasiewicz property. Finally, we consider two kinds of nonsmooth phase retrieval problems and propose an explicit iteration scheme. Numerical results verify the global convergence and illustrate the potential of our proposed algorithm.<\/jats:p>","DOI":"10.3389\/fams.2022.1031039","type":"journal-article","created":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T08:08:00Z","timestamp":1669104480000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Bregman iterative regularization using model functions for nonconvex nonsmooth optimization"],"prefix":"10.3389","volume":"8","author":[{"given":"Haoxing","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongxia","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lizhi","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2022,11,22]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1137\/040605412","article-title":"An iterative regularization method for total variation-based image restoration","volume":"4","author":"Osher","year":"2005","journal-title":"SIAM J Multiscale Model Simulat"},{"key":"B2","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1137\/070703983","article-title":"Bregman iterative algorithms for \u21131-minimization with applications to compressed sensing","volume":"1","author":"Yin","year":"2008","journal-title":"SIAM J Imaging Sci"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1237","DOI":"10.1137\/130936269","article-title":"The linearized bregman method via split feasibility problems: analysis and generalizations","volume":"7","author":"Lorenz","year":"2014","journal-title":"SIAM J Imaging Sci"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1059","DOI":"10.1137\/120863290","article-title":"Augmented \u21131 and nuclear-norm models with a globally linearly convergent algorithm","volume":"6","author":"Lai","year":"2013","journal-title":"SIAM J Imaging Sci"},{"volume-title":"Gradient methods for convex minimization: better rates under weaker conditions","year":"2013","author":"Zhang","key":"B5"},{"key":"B6","doi-asserted-by":"publisher","first-page":"814","DOI":"10.1137\/20M1357500","article-title":"Choose your path wisely: gradient descent in a Bregman distance framework","volume":"14","author":"Benning","year":"2021","journal-title":"SIAM J Imaging Sci"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1090\/mcom\/3792","article-title":"Revisiting linearized bregman iterations under lipschitz-like convexity condition","author":"Zhang","year":"2022","journal-title":"arXiv:2203.02109"},{"key":"B8","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1007\/s10107-019-01432-w","article-title":"Nonsmooth optimization using Taylor-like models: error bounds, convergence, and termination criteria","volume":"185","author":"Drusvyatskiy","year":"2021","journal-title":"Math Program"},{"key":"B9","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1007\/s10957-018-01452-0","article-title":"Non-smooth non-convex bregman minimization: unification and new algorithms","volume":"181","author":"Ochs","year":"2019","journal-title":"J Optim Theory Appl"},{"key":"B10","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1007\/s10898-021-01114-y","article-title":"Global convergence of model function based Bregman proximal minimization algorithms","volume":"83","author":"Mukkamala","year":"2021","journal-title":"J Glob Optim"},{"key":"B11","doi-asserted-by":"crossref","DOI":"10.1515\/9781400873173","volume-title":"Convex Analysis","author":"Rockafellar","year":"1970"},{"key":"B12","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/0041-5553(67)90040-7","article-title":"The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming","volume":"7","author":"Bregman","year":"1967","journal-title":"Ussr Comput Math Math Phys"},{"key":"B13","first-page":"27","article-title":"Legendre functions and the method of random bregman projections","volume":"4","author":"Bauschke","year":"1997","journal-title":"J Convex Anal"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1137\/S0363012995281742","article-title":"Proximal minimization methods with generalized Bregman functions","volume":"35","author":"Kiwiel","year":"1997","journal-title":"SIAM J Control Optim"},{"key":"B15","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1287\/moor.22.2.326","article-title":"Free-Steering relaxation methods for problems with strictly convex costs and linear constraints","volume":"22","author":"Kiwiel","year":"1997","journal-title":"Math Oper Res"},{"key":"B16","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1137\/0803026","article-title":"Convergence analysis of a proximal-like minimization algorithm using Bregman functions","volume":"3","author":"Chen","year":"1993","journal-title":"SIAM J Optim"},{"key":"B17","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1287\/moor.2016.0817","article-title":"A descent lemma beyond Lipschitz gradient continuity: first-order methods revisited and applications","volume":"42","author":"Bauschke","year":"2017","journal-title":"Math Operat Res"},{"key":"B18","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/s10107-013-0701-9","article-title":"Proximal alternating linearized minimization for nonconvex and nonsmooth problems","volume":"146","author":"Bolte","year":"2014","journal-title":"Math Program"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1205","DOI":"10.1137\/050644641","article-title":"The \u0141ojasiewicz inequality for nonsmooth subanalytic functions with applications to subgradient dynamical systems","volume":"17","author":"Bolte","year":"2007","journal-title":"SIAM J Optim"},{"key":"B20","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1137\/060670080","article-title":"Clarke subgradients of stratifiable functions","volume":"18","author":"Bolte","year":"2007","journal-title":"SIAM J Optim"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974997","article-title":"First-Order Methods in Optimization","author":"Beck","year":"2017","journal-title":"SIAM-Soc Ind Appl Math"},{"volume-title":"Principles of Mathematical Analysis","year":"1976","author":"Rubin","key":"B22"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2204.03554","article-title":"Phase retrieval: from computational imaging to machine learning","author":"Dong","year":"2022","journal-title":"arXiv:2204.03554."},{"key":"B24","doi-asserted-by":"publisher","first-page":"22924","DOI":"10.1073\/pnas.1908018116","article-title":"The importance of better models in stochastic optimization","volume":"116","author":"Hilal","year":"2019","journal-title":"Proc Natl Acad Sci USA"},{"key":"B25","doi-asserted-by":"publisher","first-page":"4574","DOI":"10.1109\/TSP.2018.2855667","article-title":"Phase retrieval algorithm via nonconvex minimization using a smoothing function","volume":"66","author":"Pinilla","year":"2018","journal-title":"IEEE Trans Signal Process"},{"key":"B26","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1137\/14095697X","article-title":"An accelerated linearized alternating direction method of multipliers","volume":"8","author":"Ouyang","year":"2015","journal-title":"SIAM J Imaging Sci"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1985","DOI":"10.1109\/TIT.2015.2399924","article-title":"Phase retrieval via wirtinger flow: theory and algorithms","volume":"61","author":"Cand\u00e8s","year":"2015","journal-title":"IEEE Trans Inf Theory"}],"container-title":["Frontiers in Applied Mathematics and Statistics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fams.2022.1031039\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T08:08:08Z","timestamp":1669104488000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fams.2022.1031039\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,22]]},"references-count":27,"alternative-id":["10.3389\/fams.2022.1031039"],"URL":"https:\/\/doi.org\/10.3389\/fams.2022.1031039","relation":{},"ISSN":["2297-4687"],"issn-type":[{"type":"electronic","value":"2297-4687"}],"subject":[],"published":{"date-parts":[[2022,11,22]]},"article-number":"1031039"}}