{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T05:10:39Z","timestamp":1772082639476,"version":"3.50.1"},"reference-count":78,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T00:00:00Z","timestamp":1739750400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T00:00:00Z","timestamp":1739750400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000145","name":"Division of Information and Intelligent Systems","doi-asserted-by":"publisher","award":["1844403"],"award-info":[{"award-number":["1844403"]}],"id":[{"id":"10.13039\/100000145","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s10994-024-06650-8","type":"journal-article","created":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T22:44:46Z","timestamp":1739832286000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Unified convergence analysis for adaptive optimization with moving average estimator"],"prefix":"10.1007","volume":"114","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2153-2287","authenticated-orcid":false,"given":"Zhishuai","family":"Guo","sequence":"first","affiliation":[]},{"given":"Yi","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Wotao","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Rong","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Tianbao","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,17]]},"reference":[{"key":"6650_CR1","unstructured":"Abadi, M., Agarwal, A., Barham, P., et al.(2015). TensorFlow: Large-scale machine learning on heterogeneous systems. https:\/\/www.tensorflow.org\/ Software available from tensorflow.org."},{"key":"6650_CR2","unstructured":"Alistarh, D., Grubic, D., Li, J., Tomioka, R., & Vojnovic, M. (2017). Qsgd: Communication-efficient sgd via gradient quantization and encoding. In Advances in neural information processing systems (Vol. 30, pp. 1709\u20131720)."},{"key":"6650_CR3","unstructured":"Allen-Zhu, Z. (2018). How to make the gradients small stochastically: Even faster convex and nonconvex sgd. In Advances in neural information processing systems, vol. 31."},{"key":"6650_CR4","unstructured":"Arjevani, Y., Carmon, Y., Duchi, J.C., Foster, D.J., Srebro, N., & Woodworth, B. (2019). Lower bounds for non-convex stochastic optimization. arXiv:1912.02365."},{"key":"6650_CR5","unstructured":"Bo\u0163, R.I., & B\u00f6hm, A. (2020). Alternating proximal-gradient steps for (stochastic) nonconvex-concave minimax problems. arXiv:2007.13605."},{"key":"6650_CR6","unstructured":"Bot, R.I., Csetnek, E.R., & Nguyen, D.-K. (2022). Fast ogda in continuous and discrete time. arXiv:2203.10947."},{"issue":"3","key":"6650_CR7","doi-asserted-by":"crossref","first-page":"1884","DOI":"10.1137\/21M1465470","volume":"33","author":"RI Bo\u0163","year":"2023","unstructured":"Bo\u0163, R. I., & B\u00f6hm, A. (2023). Alternating proximal-gradient steps for (stochastic) nonconvex-concave minimax problems. SIAM Journal on Optimization, 33(3), 1884\u20131913.","journal-title":"SIAM Journal on Optimization"},{"key":"6650_CR8","unstructured":"Chavdarova, T., Gidel, G., Fleuret, F., & Lacoste-Julien, S. (2019). Reducing noise in GAN training with variance reduced extragradient. In Advances in neural information processing systems, vol. 32."},{"key":"6650_CR9","unstructured":"Chen, T., Guo, Z., Sun, Y., & Yin, W. (2021). Cada: Communication-adaptive distributed adam. In International conference on artificial intelligence and statistics (pp. 613\u2013621)."},{"key":"6650_CR10","unstructured":"Chen, X., Liu, S., Sun, R., & Hong, M. (2019). On the convergence of A class of adam-type algorithms for non-convex optimization. In 7th international conference on learning representations (ICLR)."},{"key":"6650_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Z., Ma, S., & Zhou, Y. (2022). Accelerated proximal alternating gradient-descent-ascent for nonconvex minimax machine learning. In 2022 IEEE international symposium on information theory (ISIT) (pp. 672\u2013677).","DOI":"10.1109\/ISIT50566.2022.9834691"},{"key":"6650_CR12","doi-asserted-by":"crossref","unstructured":"Chen, J., Zhou, D., Tang, Y., Yang, Z., Cao, Y., & Gu, Q. (2020). Closing the generalization gap of adaptive gradient methods in training deep neural networks. In Proceedings of the twenty-ninth international joint conference on artificial intelligence (IJCAI) (pp. 3267\u20133275).","DOI":"10.24963\/ijcai.2020\/452"},{"key":"6650_CR13","unstructured":"Chollet, F., textitet al. (2015). Keras. https:\/\/github.com\/fchollet\/keras. GitHub."},{"key":"6650_CR14","unstructured":"Cutkosky, A., & Orabona, F. (2019). Momentum-based variance reduction in non-convex SGD. In Advances in neural information processing systems (Vol. 32, pp. 15236\u201315245)."},{"issue":"1","key":"6650_CR15","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1137\/18M1178244","volume":"29","author":"D Davis","year":"2019","unstructured":"Davis, D., & Drusvyatskiy, D. (2019). Stochastic model-based minimization of weakly convex functions. SIAM Journal on Optimization, 29(1), 207\u2013239.","journal-title":"SIAM Journal on Optimization"},{"key":"6650_CR16","unstructured":"D\u00e9fossez, A., Bottou, L., Bach, F., & Usunier, N. (2020). A simple convergence proof of adam and adagrad. arXiv:2003.02395."},{"key":"6650_CR17","unstructured":"Dou, Z., & Li, Y. (2021). On the one-sided convergence of adam-type algorithms in non-convex non-concave min-max optimization. arXiv:2109.14213."},{"issue":"Jul","key":"6650_CR18","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi, J., Hazan, E., & Singer, Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12(Jul), 2121\u20132159.","journal-title":"Journal of Machine Learning Research"},{"key":"6650_CR19","unstructured":"Fang, C., Li, C.J., Lin, Z., & Zhang, T. (2018). Spider: Near-optimal non-convex optimization via stochastic path-integrated differential estimator. In Advances in neural information processing systems (pp. 689\u2013699)."},{"key":"6650_CR20","unstructured":"Ghadimi, S., & Wang, M. (2018). Approximation methods for bilevel programming. arXiv:1802.02246."},{"issue":"4","key":"6650_CR21","doi-asserted-by":"crossref","first-page":"2341","DOI":"10.1137\/120880811","volume":"23","author":"S Ghadimi","year":"2013","unstructured":"Ghadimi, S., & Lan, G. (2013). Stochastic first-and zeroth-order methods for nonconvex stochastic programming. SIAM Journal on Optimization, 23(4), 2341\u20132368.","journal-title":"SIAM Journal on Optimization"},{"issue":"1\u20132","key":"6650_CR22","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1007\/s10107-015-0871-8","volume":"156","author":"S Ghadimi","year":"2016","unstructured":"Ghadimi, S., & Lan, G. (2016). Accelerated gradient methods for nonconvex nonlinear and stochastic programming. Mathematical Programming, 156(1\u20132), 59\u201399.","journal-title":"Mathematical Programming"},{"issue":"1","key":"6650_CR23","doi-asserted-by":"crossref","first-page":"960","DOI":"10.1137\/18M1230542","volume":"30","author":"S Ghadimi","year":"2020","unstructured":"Ghadimi, S., Ruszczynski, A., & Wang, M. (2020). A single timescale stochastic approximation method for nested stochastic optimization. SIAM Journal on Optimization, 30(1), 960\u2013979.","journal-title":"SIAM Journal on Optimization"},{"key":"6650_CR24","unstructured":"Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., & Dahl, G.E. (2017). Neural message passing for quantum chemistry. In International conference on machine learning (pp. 1263\u20131272)."},{"key":"6650_CR25","unstructured":"Guo, Z., Yuan, Z., Yan, Y., & Yang, T. (2020). Fast objective and duality gap convergence for non-convex strongly-concave min\u2013max problems. arXiv:2006.06889."},{"key":"6650_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"6650_CR27","unstructured":"Hong, M., Wai, H.-T., Wang, Z., & Yang, Z. (2020). A two-timescale framework for bilevel optimization: Complexity analysis and application to actor-critic. arXiv:2007.05170."},{"key":"6650_CR28","first-page":"16223","volume":"33","author":"Y-G Hsieh","year":"2020","unstructured":"Hsieh, Y.-G., Iutzeler, F., Malick, J., & Mertikopoulos, P. (2020). Explore aggressively, update conservatively: Stochastic extragradient methods with variable stepsize scaling. Advances in Neural Information Processing Systems, 33, 16223\u201316234.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6650_CR29","unstructured":"Huang, F., Gao, S., Pei, J., & Huang, H. (2020). Accelerated zeroth-order momentum methods from mini to minimax optimization. arXiv:2008.08170."},{"key":"6650_CR30","unstructured":"Huang, F., Li, J., & Huang, H. (2021). Super-adam: Faster and universal framework of adaptive gradients. arXiv:2106.08208."},{"issue":"1","key":"6650_CR31","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1287\/10-SSY011","volume":"1","author":"A Juditsky","year":"2011","unstructured":"Juditsky, A., Nemirovski, A., Tauvel, C., et al. (2011). Solving variational inequalities with stochastic mirror-prox algorithm. Stochastic Systems, 1(1), 17\u201358.","journal-title":"Stochastic Systems"},{"key":"6650_CR32","doi-asserted-by":"crossref","unstructured":"Karimi, H., Nutini, J., & Schmidt, M. (2016). Linear convergence of gradient and proximal-gradient methods under the Polyak-\u0142ojasiewicz condition. In Joint European conference on machine learning and knowledge discovery in databases (pp. 795\u2013811).","DOI":"10.1007\/978-3-319-46128-1_50"},{"key":"6650_CR33","unstructured":"Kingma, D.P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv:1412.6980."},{"key":"6650_CR34","unstructured":"Krizhevsky, A., Hinton, G., et al. (2009). Learning multiple layers of features from tiny images. Technical Report."},{"key":"6650_CR35","unstructured":"Li, X., & Orabona, F. (2019). On the convergence of stochastic gradient descent with adaptive stepsizes. In The 22nd international conference on artificial intelligence and statistics (aistats) (pp. 983\u2013992)."},{"key":"6650_CR36","unstructured":"Lin, T., Jin, C., & Jordan, M. (2020a). On gradient descent ascent for nonconvex-concave minimax problems. In International conference on machine learning (ICML) (pp. 6083\u20136093)."},{"key":"6650_CR37","unstructured":"Lin, T., Jin, C., & Jordan, M.I. (2020b). Near-optimal algorithms for minimax optimization. In Conference on learning theory (colt) (pp. 2738\u20132779)."},{"key":"6650_CR38","first-page":"1792","volume":"34","author":"H Li","year":"2021","unstructured":"Li, H., Tian, Y., Zhang, J., & Jadbabaie, A. (2021). Complexity lower bounds for nonconvex-strongly-concave min\u2013max optimization. Advances in Neural Information Processing Systems, 34, 1792\u20131804.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6650_CR39","unstructured":"Liu, L., Jiang, H., He, P., Chen, W., Liu, X., Gao, J., & Han, J. (2020). On the variance of the adaptive learning rate and beyond. In 8th international conference on learning representations (ICLR)."},{"key":"6650_CR40","unstructured":"Liu, M., Yuan, Z., Ying, Y., & Yang, T. (2020). Stochastic AUC maximization with deep neural networks. In 8th international conference on learning representations (ICLR)."},{"key":"6650_CR41","unstructured":"Liu, M., Zhang, X., Chen, Z., Wang, X., & Yang, T. (2018). Fast stochastic AUC maximization with $${O} (1\/n)$$-convergence rate. In International conference on machine learning (ICML) (pp. 3189\u20133197)."},{"key":"6650_CR42","unstructured":"Liu, M., Zhang, W., Orabona, F., & Yang, T. (2020). Adam +: A stochastic method with adaptive variance reduction. arXiv:2011.11985."},{"key":"6650_CR43","first-page":"18261","volume":"33","author":"Y Liu","year":"2020","unstructured":"Liu, Y., Gao, Y., & Yin, W. (2020). An improved analysis of stochastic gradient descent with momentum. Advances in Neural Information Processing Systems, 33, 18261\u201318271.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6650_CR44","unstructured":"Luo, L., Xiong, Y., Liu, Y., & Sun, X. (2019). Adaptive gradient methods with dynamic bound of learning rate. In 7th international conference on learning representations (ICLR)."},{"key":"6650_CR45","unstructured":"Luo, L., Ye, H., Huang, Z., & Zhang, T. (2020). Stochastic recursive gradient descent ascent for stochastic nonconvex-strongly-concave minimax problems. In Advances in neural information processing systems, Vol. 33."},{"key":"6650_CR46","doi-asserted-by":"crossref","unstructured":"McMahan, H.B., & Blum, A. (2004). Online geometric optimization in the bandit setting against an adaptive adversary. In Proceedings of the 17th annual conference on learning theory (colt) (pp. 109\u2013123).","DOI":"10.1007\/978-3-540-27819-1_8"},{"key":"6650_CR47","unstructured":"Neelakantan, A., Vilnis, L., Le, Q.V., Sutskever, I., Kaiser, L., Kurach, K., & Martens, J. (2015). Adding gradient noise improves learning for very deep networks. arXiv:1511.06807."},{"issue":"4","key":"6650_CR48","doi-asserted-by":"crossref","first-page":"1574","DOI":"10.1137\/070704277","volume":"19","author":"A Nemirovski","year":"2009","unstructured":"Nemirovski, A., Juditsky, A., Lan, G., & Shapiro, A. (2009). Robust stochastic approximation approach to stochastic programming. SIAM Journal on Optimization, 19(4), 1574\u20131609.","journal-title":"SIAM Journal on Optimization"},{"key":"6650_CR49","first-page":"10","volume":"88","author":"Y Nesterov","year":"2012","unstructured":"Nesterov, Y. (2012). How to make the gradients small. Optima. Mathematical Optimization Society Newsletter, 88, 10\u201311.","journal-title":"Optima. Mathematical Optimization Society Newsletter"},{"key":"6650_CR50","unstructured":"Nouiehed, M., Sanjabi, M., Huang, T., Lee, J.D., & Razaviyayn, M. (2019). Solving a class of non-convex min\u2013max games using iterative first order methods. In Advances in neural information processing systems (Vol. 32, pp. 14905\u201314916)."},{"issue":"110","key":"6650_CR51","first-page":"1","volume":"21","author":"NH Pham","year":"2020","unstructured":"Pham, N. H., Nguyen, L. M., Phan, D. T., & Tran-Dinh, Q. (2020). ProxSARAH: An efficient algorithmic framework for stochastic composite nonconvex optimization. Journal of Machine Learning Research, 21(110), 1\u201348.","journal-title":"Journal of Machine Learning Research"},{"key":"6650_CR52","unstructured":"Qiu, S., Yang, Z., Wei, X., Ye, J., & Wang, Z. (2020). Single-timescale stochastic nonconvex-concave optimization for smooth nonlinear td learning. arXiv:2008.10103."},{"issue":"3","key":"6650_CR53","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.1080\/10556788.2021.1895152","volume":"37","author":"H Rafique","year":"2021","unstructured":"Rafique, H., Liu, M., Lin, Q., & Yang, T. (2021). Weakly-convex-concave min\u2013max optimization: Provable algorithms and applications in machine learning. Optimization Methods and Software, 37(3), 1087\u20131121.","journal-title":"Optimization Methods and Software"},{"key":"6650_CR54","unstructured":"Reddi, S.J., Kale, S., & Kumar, S. (2018). On the convergence of ADAM and beyond. In 6th international conference on learning representations (ICLR)."},{"key":"6650_CR55","unstructured":"Savarese, P. (2019). On the convergence of adabound and its connection to sgd. arXiv:1908.04457."},{"key":"6650_CR56","unstructured":"Shi, N., Li, D., Hong, M., & Ruoyu, S. (2021). RMSprop converges with proper hyper-parameter. In 9th international conference on learning representations (ICLR)."},{"key":"6650_CR57","unstructured":"Tieleman, T., & Hinton, G. (2012). Lecture 6.5-rmsprop, coursera: Neural networks for machine learning. University of Toronto, Technical Report."},{"key":"6650_CR58","first-page":"11096","volume":"33","author":"Q Tran-Dinh","year":"2020","unstructured":"Tran-Dinh, Q., Liu, D., & Nguyen, L. M. (2020). Hybrid variance-reduced SGD algorithms for minimax problems with nonconvex-linear function. Advances in Neural Information Processing Systems, 33, 11096\u201311107.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6650_CR59","unstructured":"Wang, Z., Ji, K., Zhou, Y., Liang, Y., & Tarokh, V. (2019). SpiderBoost and momentum: Faster variance reduction algorithms. In Advances in neural information processing systems, (Vol. 32, pp. 2406\u20132416)."},{"key":"6650_CR60","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1007\/s10107-016-1017-3","volume":"161","author":"M Wang","year":"2017","unstructured":"Wang, M., Fang, E. X., & Liu, H. (2017). Stochastic compositional gradient descent: Algorithms for minimizing compositions of expected-value functions. Mathematical Programming, 161, 419\u2013449.","journal-title":"Mathematical Programming"},{"key":"6650_CR61","unstructured":"Wangni, J., Wang, J., Liu, J., & Zhang, T. (2018). Gradient sparsification for communication-efficient distributed optimization. In Advances in neural information processing systems (Vol. 31, pp. 1306\u20131316)."},{"key":"6650_CR62","unstructured":"Ward, R., Wu, X., & Bottou, L. (2019). AdaGrad stepsizes: Sharp convergence over nonconvex landscapes. In Proceedings of the 36th international conference on machine learning (ICML) (pp. 6677\u20136686)."},{"issue":"2","key":"6650_CR63","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1039\/C7SC02664A","volume":"9","author":"Z Wu","year":"2018","unstructured":"Wu, Z., Ramsundar, B., Feinberg, E. N., Gomes, J., Geniesse, C., Pappu, A. S., & Pande, V. (2018). Moleculenet: A benchmark for molecular machine learning. Chemical Science, 9(2), 513\u2013530.","journal-title":"Chemical Science"},{"key":"6650_CR64","unstructured":"Xu, Z., Zhang, H., Xu, Y., & Lan, G. (2020). A unified single-loop alternating gradient projection algorithm for nonconvex-concave and convex-nonconcave minimax problems. arXiv:2006.02032."},{"key":"6650_CR65","unstructured":"Yan, Y., Xu, Y., Lin, Q., Liu, W., & Yang, T. (2020). Optimal epoch stochastic gradient descent ascent methods for min-max optimization. In Advances in neural information processing systems, Vol. 33."},{"key":"6650_CR66","unstructured":"Yang, J., Kiyavash, N., & He, N. (2020). Global convergence and variance reduction for a class of nonconvex-nonconcave minimax problems. In Advances in neural information processing systems, Vol. 33"},{"key":"6650_CR67","unstructured":"Yang, T., Lin, Q., & Li, Z. (2016). Unified convergence analysis of stochastic momentum methods for convex and non-convex optimization. arXiv:1604.03257"},{"key":"6650_CR68","unstructured":"Yang, J., Orvieto, A., Lucchi, A., & He, N. (2022). Faster single-loop algorithms for minimax optimization without strong concavity. In International conference on artificial intelligence and statistics (pp. 5485\u20135517)."},{"issue":"2","key":"6650_CR69","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1007\/s12532-021-00214-w","volume":"14","author":"Y Yan","year":"2022","unstructured":"Yan, Y., & Xu, Y. (2022). Adaptive primal-dual stochastic gradient method for expectation-constrained convex stochastic programs. Mathematical Programming Computation, 14(2), 319\u2013363.","journal-title":"Mathematical Programming Computation"},{"key":"6650_CR70","unstructured":"Ying, Y., Wen, L., & Lyu, S. (2016). Stochastic online AUC maximization. In Advances in neural information processing systems (pp. 451\u2013459)."},{"key":"6650_CR71","unstructured":"Yu, H., Jin, R., & Yang, S. (2019). On the linear speedup analysis of communication efficient momentum SGD for distributed non-convex optimization. In Proceedings of the 36th international conference on machine learning (ICML) (pp. 7184\u20137193)."},{"key":"6650_CR72","unstructured":"Zaheer, M., Reddi, S.J., Sachan, D.S., Kale, S., & Kumar, S. (2018). Adaptive methods for nonconvex optimization. In Advances in neural information processing systems (Vol. 31, pp. 9815\u20139825)."},{"key":"6650_CR73","unstructured":"Zhang, Y., Chen, C., Shi, N., Sun, R., & Luo, Z.-Q. (2022). Adam can converge without any modification on update rules. arXiv:2208.09632."},{"key":"6650_CR74","unstructured":"Zhang, H., Li, J., Kara, K., Alistarh, D., Liu, J., & Zhang, C. (2017). ZipML: Training linear models with end-to-end low precision, and a little bit of deep learning. In Proceedings of the 34th international conference on machine learning (ICML) (pp. 4035\u20134043)."},{"key":"6650_CR75","unstructured":"Zhang, S., Yang, J., Guzm\u00e1n, C., Kiyavash, N., & He, N. (2021). The complexity of nonconvex-strongly-concave minimax optimization. In Uncertainty in artificial intelligence (pp. 482\u2013492)."},{"key":"6650_CR76","first-page":"21668","volume":"35","author":"X Zhang","year":"2022","unstructured":"Zhang, X., Aybat, N. S., & Gurbuzbalaban, M. (2022). Sapd+: An accelerated stochastic method for nonconvex-concave minimax problems. Advances in Neural Information Processing Systems, 35, 21668\u201321681.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6650_CR77","unstructured":"Zou, F., & Shen, L. (2018). On the convergence of Adagrad with momentum for training deep neural networks, Vol. 2, No 3, p. 5. arXiv preprint arXiv:1808.03408."},{"key":"6650_CR78","doi-asserted-by":"crossref","unstructured":"Zou, F., Shen, L., Jie, Z., Zhang, W., & Liu, W. (2019). A sufficient condition for convergences of Adam and RMSProp. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 11127\u201311135).","DOI":"10.1109\/CVPR.2019.01138"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-024-06650-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-024-06650-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-024-06650-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T01:03:16Z","timestamp":1771290196000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-024-06650-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,17]]},"references-count":78,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["6650"],"URL":"https:\/\/doi.org\/10.1007\/s10994-024-06650-8","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,17]]},"assertion":[{"value":"14 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}],"article-number":"86"}}