{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T09:10:33Z","timestamp":1778231433505,"version":"3.51.4"},"reference-count":41,"publisher":"Institute for Operations Research and the Management Sciences (INFORMS)","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Mathematics of OR"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:p>Anderson mixing (AM) method is a popular approach for accelerating fixed-point iterations by leveraging historical information from previous steps. In this paper, we introduce the Riemannian Anderson mixing (RAM) method, an extension of AM to Riemannian manifolds, and analyze its local linear convergence under reasonable assumptions. Unlike other extrapolation-based algorithms on Riemannian manifolds, RAM does not require computing the inverse retraction or inverse exponential mapping and has a lower per-iteration cost. Furthermore, we propose a variant of RAM called regularized RAM (RRAM), which establishes global convergence and exhibits similar local convergence properties to RAM. Our proof relies on careful error estimations based on the local geometry of Riemannian manifolds. Finally, we present experimental results on various manifold optimization problems that demonstrate the superior performance of our proposed methods over existing Riemannian gradient descent and limited-memory Broyden-Fletcher-Goldfarb-Shanno (LBFGS) approaches.<\/jats:p>\n                  <jats:p>Funding: This research was supported by the National Key R&amp;D Program of China [Grant 2021YFA1001300] and the National Natural Science Foundation of China [Grant 12271291].<\/jats:p>","DOI":"10.1287\/moor.2023.0284","type":"journal-article","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T11:23:47Z","timestamp":1745580227000},"page":"905-937","source":"Crossref","is-referenced-by-count":0,"title":["Riemannian Anderson Mixing Methods for Minimizing\n                    <i>C<\/i>\n                    <sup>2<\/sup>\n                    Functions on Riemannian Manifolds"],"prefix":"10.1287","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2347-677X","authenticated-orcid":false,"given":"Zanyu","family":"Li","sequence":"first","affiliation":[{"name":"Yau Mathematical Sciences Center, Tsinghua University, Beijing 100084, China; and Department of Mathematical Sciences, Tsinghua University, Beijing 100084, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1201-1212","authenticated-orcid":false,"given":"Chenglong","family":"Bao","sequence":"additional","affiliation":[{"name":"Yau Mathematical Sciences Center, Tsinghua University, Beijing 100084, China; and Yanqi Lake Beijing Institute of Mathematical Sciences and Applications, Beijing 101408, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"109","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-005-0179-9"},{"key":"B2","volume-title":"Optimization Algorithms on Matrix Manifolds","author":"Absil PA","year":"2009"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-020-01505-1"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1145\/321296.321305"},{"key":"B5","doi-asserted-by":"crossref","unstructured":"Boumal N (2023)\n                      An Introduction to Optimization on Smooth Manifolds\n                      (Cambridge University Press, Cambridge, UK).","DOI":"10.1017\/9781009166164"},{"issue":"1","key":"B6","first-page":"1455","volume":"15","author":"Boumal N","year":"2014","journal-title":"J. Machine Learn. Res."},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-002-0352-8"},{"key":"B8","unstructured":"Cho M, Lee J (2017) Riemannian approach to batch normalization.\n                      NIPS\u201917 Proc. 31st Internat. Conf. Neural Inform. Processing Systems\n                      (Curran Associates Inc. Red Hook, NY), 5231\u20135241."},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1051\/m2an\/2021069"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmaa.2017.04.011"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1137\/19M1245384"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1002\/nla.617"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022675100677"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1145\/227683.227684"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1137\/17M1142478"},{"key":"B16","first-page":"1","volume":"194","author":"Huang W","year":"2021","journal-title":"Math. Programming"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1137\/17M1127582"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1093\/imanum\/drx015"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.3160300502"},{"key":"B20","unstructured":"Kim J, Yang I (2022) Nesterov acceleration for Riemannian optimization. Preprint, submitted February 4, https:\/\/arxiv.org\/abs\/2202.02036."},{"key":"B21","doi-asserted-by":"crossref","unstructured":"Kovnatsky A, Glashoff K, Bronstein MM (2016) MADMM: A generic algorithm for non-smooth optimization on manifolds. Leibe B, Matas J, Sebe N, Welling M, eds.\n                      Comput. Vision, ECCV 2016\n                      , Lecture Notes in Computer Science, vol. 9909 (Springer, Cham, Switzerland), 680\u2013696.","DOI":"10.1007\/978-3-319-46454-1_41"},{"key":"B22","doi-asserted-by":"crossref","unstructured":"Levin E, Kileel J, Boumal N (2023) Finding stationary points on bounded-rank matrices: A geometric hurdle and a smooth remedy.\n                      Math. Programming\n                      199(1):831\u2013864.","DOI":"10.1007\/s10107-022-01851-2"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.18.11.620"},{"issue":"3","key":"B24","first-page":"543","volume":"269","author":"Nesterov YE","year":"1983","journal-title":"Dokl. Akad. Nauk SSSR"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1093\/imanum\/draa095"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2012.09.008"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1137\/11082885X"},{"key":"B28","doi-asserted-by":"crossref","unstructured":"Sato H (2022) Riemannian conjugate gradient methods: General framework and specific algorithms with convergence analyses.\n                      SIAM J. Optim.\n                      32(4):2690\u20132717.","DOI":"10.1137\/21M1464178"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1137\/17M1116787"},{"key":"B30","unstructured":"Sun Y, Flammarion N, Fazel M (2019) Escaping from saddle points on Riemannian manifolds.\n                      Proc. 33rd Internat. Conf. Neural Inform. Processing Systems\n                      (Curran Associates Inc. Red Hook, NY), 7276\u20137286."},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1137\/130919398"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1137\/110845768"},{"key":"B33","unstructured":"Wei F, Bao C, Liu Y (2021) A class of short-term recurrence Anderson mixing methods and their applications.\n                      Internat. Conf. Learn. Representations\n                      (IEEE Information Theory Society, Piscataway, NJ)."},{"key":"B34","unstructured":"Wei F, Bao C, Liu Y (2021) Stochastic Anderson mixing for nonconvex stochastic optimization.\n                      NIPS\u201921 Proc. 35th Internat. Conf. Neural Inform. Processing Systems\n                      (Curran Associates Inc. Red Hook, NY), 22995\u201323008."},{"key":"B35","doi-asserted-by":"crossref","unstructured":"Zass R, Shashua A (2006) Nonnegative sparse PCA.\n                      NIPS\u201906 Proc. 20th Internat. Conf. Neural Inform. Processing Systems\n                      (MIT Press, Cambridge, MA), 1561\u20131568.","DOI":"10.7551\/mitpress\/7503.003.0200"},{"key":"B36","first-page":"1617","volume-title":"Conf. Learning Theory","author":"Zhang H","year":"2016"},{"key":"B37","unstructured":"Zhang H, Sra S (2018) An estimate sequence for geodesically convex optimization.\n                      Conf. Learning Theory\n                      (PMLR, New York), 1703\u20131723."},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-019-01418-8"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1137\/130932934"},{"key":"B40","doi-asserted-by":"crossref","unstructured":"Zhang Y, Lau Y, Hw K, Cheung S, Pasupathy A, Wright J (2017) On the global geometry of sphere-constrained sparse blind deconvolution.\n                      Proc. IEEE Conf. Comput. Vision Pattern Recognition\n                      (IEEE, Piscataway, NJ), 4894\u20134902.","DOI":"10.1109\/CVPR.2017.466"},{"key":"B41","doi-asserted-by":"crossref","unstructured":"Zhou Y, Bao C, Ding C, Zhu J (2023) A semismooth Newton based augmented Lagrangian method for nonsmooth optimization on matrix manifolds.\n                      Math. Programming\n                      201(1):1\u201361.","DOI":"10.1007\/s10107-022-01898-1"}],"container-title":["Mathematics of Operations Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubsonline.informs.org\/doi\/pdf\/10.1287\/moor.2023.0284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T08:25:33Z","timestamp":1778228733000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubsonline.informs.org\/doi\/10.1287\/moor.2023.0284"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":41,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["10.1287\/moor.2023.0284"],"URL":"https:\/\/doi.org\/10.1287\/moor.2023.0284","relation":{},"ISSN":["0364-765X","1526-5471"],"issn-type":[{"value":"0364-765X","type":"print"},{"value":"1526-5471","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}