{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T14:48:34Z","timestamp":1767970114444,"version":"3.49.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T00:00:00Z","timestamp":1761609600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T00:00:00Z","timestamp":1761609600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12271473"],"award-info":[{"award-number":["12271473"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20426"],"award-info":[{"award-number":["U21A20426"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Adv Comput Math"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s10444-025-10263-7","type":"journal-article","created":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T07:54:06Z","timestamp":1761638046000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust kernel-based gradient descent with random features"],"prefix":"10.1007","volume":"51","author":[{"given":"Qi","family":"Hong","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7134-6725","authenticated-orcid":false,"given":"Zheng-Chu","family":"Guo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,28]]},"reference":[{"key":"10263_CR1","unstructured":"Avron, H., Kapralov, M., Musco, C., Musco, C., Velingker, A., Zandieh, A.: Random Fourier features for kernel ridge regression: approximation bounds and statistical guarantees. In: International conference on machine learning, pp. 253\u2013262. PMLR (2017)"},{"key":"10263_CR2","first-page":"1","volume":"18","author":"F Bach","year":"2017","unstructured":"Bach, F.: On the equivalence between kernel quadrature rules and random feature expansions. J. Mach. Learn. Res. 18, 1\u201338 (2017)","journal-title":"J. Mach. Learn. Res."},{"key":"10263_CR3","doi-asserted-by":"crossref","unstructured":"Bach, F.R, Jordan, M.I.: Predictive low-rank decomposition for kernel methods. In Proceedings of the 22nd international conference on machine learning, pp. 33\u201340 (2005)","DOI":"10.1145\/1102351.1102356"},{"key":"10263_CR4","doi-asserted-by":"crossref","unstructured":"Barron, J.T.: A general and adaptive robust loss function. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 4331\u20134339 (2019)","DOI":"10.1109\/CVPR.2019.00446"},{"key":"10263_CR5","doi-asserted-by":"crossref","unstructured":"Black, M.J., Anandan, P.: Parametric and piecewise-smooth flow fields: the robust estimation of multiple motions. Comp. Vision. Image Underst. 63, 75\u2013104 (1996)","DOI":"10.1006\/cviu.1996.0006"},{"key":"10263_CR6","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1007\/s10208-017-9359-7","volume":"18","author":"G Blanchard","year":"2018","unstructured":"Blanchard, G., M\u00fccke, N.: Optimal rates for regularization of statistical inverse learning problems. Found. Comput. Math. 18, 971\u20131013 (2018)","journal-title":"Found. Comput. Math."},{"key":"10263_CR7","doi-asserted-by":"crossref","unstructured":"Boucheron, S., Lugosi, G., Bousquet, O.: Concentration inequalities. In advanced lectures on machine learning (2004)","DOI":"10.1007\/978-3-540-28650-9_9"},{"key":"10263_CR8","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1109\/TGRS.2005.846154","volume":"43","author":"G Camps-Valls","year":"2005","unstructured":"Camps-Valls, G., Bruzzone, L.: Kernel-based methods for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 43, 1351\u20131362 (2005)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10263_CR9","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/s10208-006-0196-8","volume":"7","author":"A Caponnetto","year":"2007","unstructured":"Caponnetto, A., De Vito, E.: Optimal rates for the regularized least-squares algorithm. Found. Comput. Math. 7, 331\u2013368 (2007)","journal-title":"Found. Comput. Math."},{"key":"10263_CR10","unstructured":"Carratino, L., Rudi, A., Rosasco, L.: Learning with SGD and random features. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"10263_CR11","doi-asserted-by":"crossref","unstructured":"Cucker, F., Zhou, D.\u00a0X.: Learning theory: an approximation theory viewpoint. Cambridge University Press (2007)","DOI":"10.1017\/CBO9780511618796"},{"key":"10263_CR12","unstructured":"Dekel, O., Shalev-Shwartz, S., Singer, Y.: The Forgetron: a kernel-based perceptron on a fixed budget. Adv. Neural Inf. Process. Syst. 18 (2005)"},{"key":"10263_CR13","unstructured":"Fair, R.\u00a0C.: On the robust estimation of econometric models. In annals of economic and social measurement, vol.\u00a03, pp. 667\u2013677. NBER (1974)"},{"key":"10263_CR14","unstructured":"Feng, Y., Huang, X., Shi, L., Yang, Y., Suykens, J.\u00a0A., et\u00a0al.: Learning with the maximum correntropy criterion induced losses for regression. J. Mach. Learn. Res. 16(30), 993\u20131034 (2015)"},{"key":"10263_CR15","doi-asserted-by":"publisher","first-page":"827","DOI":"10.1090\/S0002-9939-1993-1132412-1","volume":"118","author":"J Fujii","year":"1993","unstructured":"Fujii, J., Fujii, M., Furuta, T., Nakamoto, R.: Norm inequalities equivalent to heinz inequality. Proc. Am. Math. Soc. 118, 827\u2013830 (1993)","journal-title":"Proc. Am. Math. Soc."},{"key":"10263_CR16","doi-asserted-by":"crossref","unstructured":"Guan, N., Liu, T., Zhang, Y., Tao, D., Davis, L.\u00a0S.: Truncated Cauchy non-negative matrix factorization. IEEE Trans. Patt. Anal. Mach. Intel. 41(1), 246\u2013259 (2017)","DOI":"10.1109\/TPAMI.2017.2777841"},{"key":"10263_CR17","unstructured":"Guo, Z.-C., Christmann, A., Shi, L.: Optimality of robust online learning. Found. Comput. Math. 1\u201329 (2023)"},{"issue":"5","key":"10263_CR18","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1007\/s10208-023-09616-9","volume":"24","author":"Z-C Guo","year":"2024","unstructured":"Guo, Z.-C., Christmann, A., Shi, L.: Optimality of robust online learning. Found. Comput. Math. 24(5), 1455\u20131483 (2024)","journal-title":"Found. Comput. Math."},{"key":"10263_CR19","doi-asserted-by":"crossref","unstructured":"Guo, Z.-C., Ting, H., Shi, L.: Gradient descent for robust kernel-based regression. Inverse Probl. 34 (2018)","DOI":"10.1088\/1361-6420\/aabe55"},{"key":"10263_CR20","doi-asserted-by":"crossref","unstructured":"Guo, Z.-C., Lin, S.-B., Zhou, D.-X.: Learning theory of distributed spectral algorithms. Inverse Probl. 33 (2017)","DOI":"10.1088\/1361-6420\/aa72b2"},{"key":"10263_CR21","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1016\/j.acha.2017.11.005","volume":"47","author":"Z-C Guo","year":"2019","unstructured":"Guo, Z.-C., Shi, L.: Optimal rates for coefficient-based regularized regression. Appl. Comput. Harmon. Anal. 47, 662\u2013701 (2019)","journal-title":"Appl. Comput. Harmon. Anal."},{"key":"10263_CR22","unstructured":"Hampel, F.\u00a0R., Ronchetti, E.\u00a0M., Rousseeuw, P.\u00a0J., Stahel, W.\u00a0A.: Robust statistics: the approach based on influence functions. John Wiley & Sons (2011)"},{"key":"10263_CR23","doi-asserted-by":"crossref","first-page":"1561","DOI":"10.1109\/TPAMI.2010.220","volume":"33","author":"R He","year":"2010","unstructured":"He, R., Zheng, W.-S., Bao-Gang, H.: Maximum correntropy criterion for robust face recognition. IEEE Trans. Patt. Anal. Mach. Intel. 33, 1561\u20131576 (2010)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intel."},{"key":"10263_CR24","doi-asserted-by":"crossref","unstructured":"Holland, P.\u00a0W., Welsch, R.\u00a0E.: Robust regression using iteratively reweighted least-squares. Commun. Stat.-theory Methods 6, 813\u2013827 (1977)","DOI":"10.1080\/03610927708827533"},{"key":"10263_CR25","unstructured":"Jacot, A., Gabriel, F., Hongler, C.: Neural tangent kernel: convergence and generalization in neural networks. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"10263_CR26","unstructured":"Janocha, K., Czarnecki, W.M.: On loss functions for deep neural networks in classification. Schedae Informaticae 25 (2016)"},{"key":"10263_CR27","doi-asserted-by":"crossref","unstructured":"Joachims, T.: Training linear SVMs in linear time. In Proceedings of the 12th ACM SIGKDD international conference on knowledge discovery and data mining, pp. 217\u2013226 (2006)","DOI":"10.1145\/1150402.1150429"},{"issue":"7","key":"10263_CR28","doi-asserted-by":"publisher","first-page":"2067","DOI":"10.1109\/TNNLS.2018.2876327","volume":"30","author":"X Li","year":"2018","unstructured":"Li, X., Quanmao, L., Dong, Y., Tao, D.: Robust subspace clustering by Cauchy loss function. IEEE Trans. Neural Netw. Learn. Syst. 30(7), 2067\u20132078 (2018)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10263_CR29","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1016\/j.acha.2018.09.009","volume":"48","author":"J Lin","year":"2020","unstructured":"Lin, J., Rudi, A., Rosasco, L., Cevher, V.: Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces. Appl. Comput. Harmon. Anal. 48, 868\u2013890 (2020)","journal-title":"Appl. Comput. Harmon. Anal."},{"key":"10263_CR30","doi-asserted-by":"crossref","unstructured":"Liu, F., Huang, X., Chen, Y., Suykens, J.\u00a0A.: Random features for kernel approximation: a survey on algorithms, theory, and beyond. IEEE Trans. Patt. Anal. Mach. Intel. 44(10), 7128\u20137148 (2021)","DOI":"10.1109\/TPAMI.2021.3097011"},{"key":"10263_CR31","doi-asserted-by":"crossref","first-page":"5286","DOI":"10.1109\/TSP.2007.896065","volume":"55","author":"Properties and applications in non-gaussian signal processing","year":"2007","unstructured":"Properties and applications in non-gaussian signal processing: Weifeng Liu, Puskal P Pokharel, and Jose C Principe. Correntropy. IEEE Trans. Signal Process. 55, 5286\u20135298 (2007)","journal-title":"Correntropy. IEEE Trans. Signal Process."},{"issue":"1","key":"10263_CR32","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1007\/s00365-021-09549-y","volume":"55","author":"C Ma","year":"2022","unstructured":"Ma, C., Lei, W., et al.: The Barron space and the flow-induced function spaces for neural network models. Constr. Approx. 55(1), 369\u2013406 (2022)","journal-title":"Constr. Approx."},{"key":"10263_CR33","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1002\/cpa.22008","volume":"75","author":"S Mei","year":"2022","unstructured":"Mei, S., Montanari, A.: The generalization error of random features regression: precise asymptotics and the double descent curve. Commun. Pure Appl. Math. 75, 667\u2013766 (2022)","journal-title":"Commun. Pure Appl. Math."},{"key":"10263_CR34","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.spl.2017.03.020","volume":"127","author":"S Minsker","year":"2017","unstructured":"Minsker, S.: On some extensions of Bernstein\u2019s inequality for self-adjoint operators. Stat .Prob. Lett. 127, 111\u2013119 (2017)","journal-title":"Stat .Prob. Lett."},{"key":"10263_CR35","doi-asserted-by":"crossref","unstructured":"Mizera, I., M\u00fcller, C.\u00a0H.: Breakdown points of Cauchy regression-scale estimators. Stat. Prob. Lett. 57, 79\u201389 (2002)","DOI":"10.1016\/S0167-7152(02)00057-3"},{"key":"10263_CR36","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1109\/72.914517","volume":"12","author":"K-R M\u00fcller","year":"2001","unstructured":"M\u00fcller, K.-R., Mika, S., Tsuda, K., Sch\u00f6lkopf, K.: An introduction to kernel-based learning algorithms. IEEE Trans. Neural Netw. 12, 181\u2013201 (2001)","journal-title":"IEEE Trans. Neural Netw."},{"key":"10263_CR37","unstructured":"Nguyen, M., M\u00fccke, N.: Random feature approximation for general spectral methods. arXiv preprint arXiv:2308.15434 (2023)"},{"key":"10263_CR38","unstructured":"Peng, H., Pappas, N., Yogatama, D., Schwartz, R., Smith, N.\u00a0A., Kong, L.: Random feature attention. In 9th international conference on learning representations (2021)"},{"key":"10263_CR39","unstructured":"Rahimi, A., Recht, B.: Random features for large-scale kernel machines. Adv. Neural Inf. Process. Syst. 20 (2007)"},{"key":"10263_CR40","unstructured":"Rahimi, A., Recht, B.: Weighted sums of random kitchen sinks: replacing minimization with randomization in learning. Adv. Neural Inf. Process. Syst. 21 (2008)"},{"key":"10263_CR41","unstructured":"Rudi, A., Camoriano, R., Rosasco, L.: Less is more: Nystr\u00f6m computational regularization. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"10263_CR42","unstructured":"Rudi, A., Rosasco, L.: Generalization properties of learning with random features. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"10263_CR43","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/s10208-004-0160-z","volume":"6","author":"S Smale","year":"2006","unstructured":"Smale, S., Yao, Y.: Online learning algorithms. Found. Comput. Math. 6, 145\u2013170 (2006)","journal-title":"Online learning algorithms. Found. Comput. Math."},{"key":"10263_CR44","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1142\/S0219530503000089","volume":"1","author":"S Smale","year":"2003","unstructured":"Smale, S., Zhou, D.-X.: Estimating the approximation error in learning theory. Anal. Appl. 1, 17\u201341 (2003)","journal-title":"Anal. Appl."},{"key":"10263_CR45","doi-asserted-by":"crossref","unstructured":"Steinwart, I., Christmann, A.: Support vector machines. Springer Science & Business Media (2008)","DOI":"10.1007\/978-0-387-77242-4"},{"key":"10263_CR46","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1109\/TIP.2006.888330","volume":"16","author":"H Takeda","year":"2007","unstructured":"Takeda, H., Farsiu, S., Milanfar, P.: Kernel regression for image processing and reconstruction. IEEE Trans. Image Process. 16, 349\u2013366 (2007)","journal-title":"IEEE Trans. Image Process."},{"key":"10263_CR47","doi-asserted-by":"crossref","unstructured":"Tropp, J.\u00a0A., et\u00a0al.: An introduction to matrix concentration inequalities. Found. Trends. Mach. Learn. 8, 1\u2013230 (2015)","DOI":"10.1561\/2200000048"},{"key":"10263_CR48","unstructured":"Williams, C., Seeger, M.: Using the nystr\u00f6m method to speed up kernel machines. Adv. Neural Inf. Process. Syst. 13 (2000)"},{"key":"10263_CR49","doi-asserted-by":"crossref","unstructured":"Yan, D., Huang, L., Jordan, M.\u00a0I.: Fast approximate spectral clustering. In Proceedings of the 15th ACM SIGKDD international conference on knowledge discovery and data mining, pp. 907\u2013916 (2009)","DOI":"10.1145\/1557019.1557118"},{"key":"10263_CR50","unstructured":"Yang, T., Li, Y.-F., Mahdavi, M., Jin, R., Zhou, Z.-H.: Nystr\u00f6m method vs random Fourier features: a theoretical and empirical comparison. Adv. Neural Inf. Process. Syst. 25 (2012)"},{"key":"10263_CR51","unstructured":"Yurinsky, V.: Sums and Gaussian vectors. Springer (2006)"},{"key":"10263_CR52","unstructured":"Zambon, D., Alippi, C., Livi, L.: Graph random neural features for distance-preserving graph representations. In international conference on machine learning, pp. 10968\u201310977 (2020)"},{"key":"10263_CR53","first-page":"587","volume":"25","author":"L Zhang","year":"2002","unstructured":"Zhang, L., Zhou, W.-D., Jiao, L.-C.: Kernel clustering algorithm. Chin. J. Comput.-Chin. Ed.- 25, 587\u2013590 (2002)","journal-title":"Chin. J. Comput.-Chin. Ed.-"}],"container-title":["Advances in Computational Mathematics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10444-025-10263-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10444-025-10263-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10444-025-10263-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T12:03:46Z","timestamp":1767960226000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10444-025-10263-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,28]]},"references-count":53,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["10263"],"URL":"https:\/\/doi.org\/10.1007\/s10444-025-10263-7","relation":{},"ISSN":["1019-7168","1572-9044"],"issn-type":[{"value":"1019-7168","type":"print"},{"value":"1572-9044","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,28]]},"assertion":[{"value":"26 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"51"}}