{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T09:49:50Z","timestamp":1792230590637,"version":"4.4.0"},"reference-count":47,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"3","funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["OAC-2003720"],"award-info":[{"award-number":["OAC-2003720"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Sci. Comput."],"published-print":{"date-parts":[[2023,6]]},"abstract":"<jats:p>Multigrid methods are one of the most efficient techniques for solving large sparse linear systems arising from partial differential equations (PDEs) and graph Laplacians from machine learning applications. One of the key components of multigrid is smoothing, which aims at reducing high-frequency errors on each grid level. However, finding optimal smoothing algorithms is problem-dependent and can impose challenges for many problems. In this paper, we propose an efficient adaptive framework for learning optimized smoothers from operator stencils in the form of convolutional neural networks (CNNs). The CNNs are trained on small-scale problems from a given type of PDEs based on a supervised loss function derived from multigrid convergence theories and can be applied to large-scale problems of the same class of PDEs. Numerical results on anisotropic rotated Laplacian problems and variable coefficient diffusion problems demonstrate improved convergence rates and solution time compared with classical hand-crafted relaxation methods.<\/jats:p>","DOI":"10.1137\/21m1430030","type":"journal-article","created":{"date-parts":[[2022,8,24]],"date-time":"2022-08-24T10:37:12Z","timestamp":1661337432000},"page":"S199-S225","source":"Crossref","is-referenced-by-count":29,"title":["Learning Optimal Multigrid Smoothers via Neural Networks"],"prefix":"10.1137","volume":"45","author":[{"given":"Ru","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2802-5763","authenticated-orcid":true,"given":"Ruipeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0361-0931","authenticated-orcid":true,"given":"Yuanzhe","family":"Xi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2022,8,24]]},"reference":[{"key":"atypb1","doi-asserted-by":"publisher","DOI":"10.1137\/100798806"},{"key":"atypb2","doi-asserted-by":"publisher","DOI":"10.1137\/0722038"},{"key":"atypb3","first-page":"305","volume":"30","author":"Benzi M.","year":"1999","journal-title":"Appl. Numer. Anal."},{"key":"atypb4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.06.056"},{"key":"atypb5","doi-asserted-by":"publisher","DOI":"10.1002\/pamm.201210311"},{"key":"atypb6","first-page":"257","volume-title":"Sparsity and Its Applications","author":"Brandt A.","year":"1984"},{"key":"atypb7","doi-asserted-by":"publisher","DOI":"10.1016\/0096-3003(86)90095-0"},{"key":"atypb8","first-page":"257","volume-title":"Sparsity and its Applications","author":"Brandt A.","year":"1985"},{"key":"atypb9","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827598344303"},{"key":"atypb10","volume-title":"SIAM","author":"Briggs W. L.","year":"2000"},{"key":"atypb11","doi-asserted-by":"publisher","DOI":"10.1002\/nla.2204"},{"key":"atypb12","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Chang B.","year":"2018"},{"key":"atypb13","doi-asserted-by":"publisher","DOI":"10.1080\/00207169208804097"},{"key":"atypb14","doi-asserted-by":"publisher","DOI":"10.1137\/090753589"},{"key":"atypb15","doi-asserted-by":"publisher","DOI":"10.1080\/00207169008803864"},{"key":"atypb16","doi-asserted-by":"publisher","DOI":"10.1137\/S0036142903429742"},{"key":"atypb17","first-page":"2415","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Greenfeld D.","year":"2019"},{"key":"atypb18","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827594276552"},{"key":"atypb19","doi-asserted-by":"publisher","DOI":"10.1137\/S0895479893243876"},{"key":"atypb20","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Haber E.","year":"2018"},{"key":"atypb21","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1718942115"},{"key":"atypb22","doi-asserted-by":"publisher","DOI":"10.1007\/s11425-019-9547-2"},{"key":"atypb23","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Holl P.","year":"2019"},{"key":"atypb24","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Hsieh J.-T.","year":"2019"},{"key":"atypb25","volume-title":"Deep Multigrid: Learning Prolongation and Restriction Matrices, preprint, arXiv:1711.03825 [math.NA]","author":"Katrutsa A.","year":"2017"},{"key":"atypb26","doi-asserted-by":"publisher","DOI":"10.1109\/72.712178"},{"key":"atypb27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30705-9_24"},{"key":"atypb28","first-page":"6489","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Luz I.","year":"2020"},{"key":"atypb29","doi-asserted-by":"publisher","DOI":"10.3934\/Mine.2018.1.118"},{"key":"atypb30","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2018.02.010"},{"key":"atypb31","doi-asserted-by":"publisher","DOI":"10.1137\/110835347"},{"key":"atypb32","volume-title":"PyAMG: Algebraic Multigrid Solvers in Python v$4.0$","author":"Olson L. N.","year":"2018"},{"key":"atypb33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"atypb34","volume-title":"Preliminary Proceedings of the International Multigrid Conference","author":"Ruge J. W.","year":"1983"},{"key":"atypb35","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718003"},{"key":"atypb36","volume-title":"Iterative Methods for Linear Systems of Equations: A Brief Historical Journey, preprint, arXiv:1908.01083 [math.HO]","author":"Saad Y.","year":"2020"},{"key":"atypb37","volume-title":"Optimizing Geometric Multigrid Methods with Evolutionary Computation, preprint, arXiv:1910.02749 [math.NA]","author":"Schmitt J.","year":"2019"},{"key":"atypb38","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.08.029"},{"key":"atypb39","first-page":"225","volume":"30","author":"Sterck H. D.","year":"2011","journal-title":"Comput. Informatics"},{"key":"atypb40","first-page":"381","volume-title":"Proceedings of the International Conference on Neural Networks and Signal Processing, IEEE","author":"Sun M.","year":"2003"},{"key":"atypb41","doi-asserted-by":"publisher","DOI":"10.1109\/EDAPS.2017.8277017"},{"key":"atypb42","volume-title":"Multigrid","author":"Trottenberg U.","year":"2000"},{"key":"atypb43","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492915000021"},{"key":"atypb44","doi-asserted-by":"publisher","DOI":"10.1007\/s00466-019-01715-1"},{"key":"atypb45","doi-asserted-by":"publisher","DOI":"10.1137\/0910043"},{"key":"atypb46","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492917000083"},{"key":"atypb47","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2019.06.004"}],"container-title":["SIAM Journal on Scientific Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/21M1430030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T17:53:06Z","timestamp":1787334786000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/21M1430030"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,24]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,6,30]]}},"alternative-id":["10.1137\/21M1430030"],"URL":"https:\/\/doi.org\/10.1137\/21m1430030","relation":{},"ISSN":["1064-8275","1095-7197"],"issn-type":[{"value":"1064-8275","type":"print"},{"value":"1095-7197","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,24]]}}}