{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T12:47:51Z","timestamp":1771937271152,"version":"3.50.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2023,7,20]],"date-time":"2023-07-20T00:00:00Z","timestamp":1689811200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,20]],"date-time":"2023-07-20T00:00:00Z","timestamp":1689811200000},"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":["61977046"],"award-info":[{"award-number":["61977046"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1007\/s10994-023-06356-3","type":"journal-article","created":{"date-parts":[[2023,7,20]],"date-time":"2023-07-20T19:02:21Z","timestamp":1689879741000},"page":"2871-2901","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Weighted neural tangent kernel: a generalized and improved network-induced kernel"],"prefix":"10.1007","volume":"112","author":[{"given":"Lei","family":"Tan","sequence":"first","affiliation":[]},{"given":"Shutong","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Wenxing","family":"Zhou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4285-6520","authenticated-orcid":false,"given":"Xiaolin","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,20]]},"reference":[{"key":"6356_CR1","unstructured":"Alemohammad, S., Wang, Z., Balestriero, R., & Baraniuk, R. (2021). The recurrent neural tangent kernel. In ICLR 2021: The ninth international conference on learning representations."},{"key":"6356_CR2","first-page":"6155","volume":"32","author":"Z Allen-Zhu","year":"2019","unstructured":"Allen-Zhu, Z., Li, Y., & Liang, Y. (2019). Learning and generalization in overparameterized neural networks, going beyond two layers. Advances in Neural Information Processing Systems, 32, 6155\u20136166.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6356_CR3","unstructured":"Allen-Zhu, Z., Li, Y., & Song, Z. (2018). A convergence theory for deep learning via over-parameterization. In International conference on machine learning (pp. 242\u2013252)."},{"key":"6356_CR4","unstructured":"Anselmi, F., Rosasco, L., Tan, C., & Poggio, T. A. (2015). Deep convolutional networks are hierarchical kernel machines. In CBMM memo series; 035. arXiv:1508.01084"},{"key":"6356_CR5","unstructured":"Arora, S., Cohen, N., & Hazan, E. (2018). On the optimization of deep networks: Implicit acceleration by overparameterization. In 35th International conference on machine learning, ICML 2018 (pp. 244\u2013253)."},{"key":"6356_CR6","unstructured":"Arora, S., Du, S. S., Hu, W., Li, Z., Salakhutdinov, R., & Wang, R. (2019a). On exact computation with an infinitely wide neural net. In 33rd Annual conference on neural information processing systems, NeurIPS 2019 (vol.\u00a032, pp. 8139\u20138148)."},{"key":"6356_CR7","unstructured":"Arora, S., Du, S. S., Hu, W., Li, Z., & Wang, R. (2019b). Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks. In 36th International conference on machine learning, ICML 2019 (pp. 322\u2013332)."},{"key":"6356_CR8","unstructured":"Arora, S., Du, S. S., Li, Z., Salakhutdinov, R., Wang, R., & Yu, D. (2020). Harnessing the power of infinitely wide deep nets on small-data tasks. In ICLR 2020: Eighth international conference on learning representations."},{"key":"6356_CR9","unstructured":"Belkin, M., Ma, S., & Mandal, S. (2018). To understand deep learning we need to understand kernel learning. In International conference on machine learning (pp. 540\u2013548)."},{"key":"6356_CR10","unstructured":"Brock, A., Lim, T., Ritchie, J. M., & Weston, N. J. (2017). Freezeout: Accelerate training by progressively freezing layers. In NIPS 2017 workshop on optimization: 10th NIPS workshop on optimization for machine learning."},{"key":"6356_CR11","first-page":"15847","volume":"33","author":"S Chen","year":"2020","unstructured":"Chen, S., He, H., & Su, W. J. (2020). Label-aware neural tangent kernel: Toward better generalization and local elasticity. Advances in Neural Information Processing Systems, 33, 15847\u201315858.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6356_CR12","first-page":"3036","volume":"31","author":"L Chizat","year":"2018","unstructured":"Chizat, L., & Bach, F. R. (2018). On the global convergence of gradient descent for over-parameterized models using optimal transport. Advances in Neural Information Processing Systems (NIPS), 31, 3036\u20133046.","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"6356_CR13","unstructured":"Chizat, L., Oyallon, E., & Bach, F. R. (2019). On lazy training in differentiable programming. In NeurIPS 2019\u201433rd conference on neural information processing systems (vol. 32, pp. 2937\u20132947)."},{"key":"6356_CR14","unstructured":"Cutkosky, A., & Mehta, H. (2020). Momentum improves normalized sgd. In ICML 2020: 37th international conference on machine learning (vol.\u00a01, pp. 2260\u20132268)."},{"key":"6356_CR15","first-page":"2253","volume":"29","author":"A Daniely","year":"2016","unstructured":"Daniely, A., Frostig, R., & Singer, Y. (2016). Toward deeper understanding of neural networks: The power of initialization and a dual view on expressivity. Advances in Neural Information Processing Systems, 29, 2253\u20132261.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6356_CR16","unstructured":"de\u00a0Matthews, A. G., Rowland, M., Hron, J., Turner, R. E., & Ghahramani, Z. (2018). Gaussian process behaviour in wide deep neural networks. In International conference on learning representations."},{"key":"6356_CR17","volume-title":"Some Gronwall type inequalities and applications","author":"SS Dragomir","year":"2003","unstructured":"Dragomir, S. S. (2003). Some Gronwall type inequalities and applications. Nova Science."},{"key":"6356_CR18","first-page":"5723","volume":"32","author":"SS Du","year":"2019","unstructured":"Du, S. S., Hou, K., Salakhutdinov, R. R., Poczos, B., Wang, R., & Xu, K. (2019). Graph neural tangent kernel: Fusing graph neural networks with graph kernels. Advances in Neural Information Processing Systems, 32, 5723\u20135733.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6356_CR19","unstructured":"Du, S. S., Zhai, X., Poczos, B., & Singh, A. (2018). Gradient descent provably optimizes over-parameterized neural networks. In International conference on learning representations."},{"issue":"1","key":"6356_CR20","first-page":"3133","volume":"15","author":"M Fern\u00e1ndez-Delgado","year":"2014","unstructured":"Fern\u00e1ndez-Delgado, M., Cernadas, E., Barro, S., & Amorim, D. (2014). Do we need hundreds of classifiers to solve real world classification problems? The Journal of Machine Learning Research, 15(1), 3133\u20133181.","journal-title":"The Journal of Machine Learning Research"},{"key":"6356_CR21","unstructured":"Garriga-Alonso, A., Rasmussen, C. E., & Aitchison, L. (2018). Deep convolutional networks as shallow Gaussian processes. In International conference on learning representations."},{"key":"6356_CR22","unstructured":"Ghorbani, B., Mei, S., Misiakiewicz, T., & Montanari, A. (2019). Limitations of lazy training of two-layers neural networks. arXiv preprint arXiv:1906.08899"},{"issue":"2","key":"6356_CR23","doi-asserted-by":"publisher","first-page":"1029","DOI":"10.1214\/20-AOS1990","volume":"49","author":"B Ghorbani","year":"2021","unstructured":"Ghorbani, B., Mei, S., Misiakiewicz, T., & Montanari, A. (2021). Linearized two-layers neural networks in high dimension. Annals of Statistics, 49(2), 1029\u20131054.","journal-title":"Annals of Statistics"},{"issue":"64","key":"6356_CR24","first-page":"2211","volume":"12","author":"M G\u00f6nen","year":"2011","unstructured":"G\u00f6nen, M., & Alpayd\u0131n, E. (2011). Multiple kernel learning algorithms. Journal of Machine Learning Research, 12(64), 2211\u20132268.","journal-title":"Journal of Machine Learning Research"},{"key":"6356_CR25","unstructured":"Hanin, B., & Nica, M. (2020). Finite depth and width corrections to the neural tangent kernel. In ICLR 2020: Eighth international conference on learning representations."},{"key":"6356_CR26","unstructured":"Hazan, T., & Jaakkola, T. S. (2015). Steps toward deep kernel methods from infinite neural networks. arXiv preprint arXiv:1508.05133"},{"key":"6356_CR27","volume-title":"Bayesian learning for neural networks","author":"G Hinton","year":"1995","unstructured":"Hinton, G., & Neal, R. M. (1995). Bayesian learning for neural networks. University of Toronto."},{"key":"6356_CR28","unstructured":"Hu, W., Li, Z., & Yu, D. (2019). Understanding generalization of deep neural networks trained with noisy labels. arXiv preprint arXiv:1905.11368"},{"key":"6356_CR29","unstructured":"Huang, J., & Yau, H. T. (2020). Dynamics of deep neural networks and neural tangent hierarchy. In ICML 2020: 37th international conference on machine learning (vol. 1, pp. 4542\u20134551)."},{"key":"6356_CR30","first-page":"8571","volume":"31","author":"A Jacot","year":"2018","unstructured":"Jacot, A., Gabriel, F., & Hongler, C. (2018). Neural tangent kernel: Convergence and generalization in neural networks. Advances in Neural Information Processing Systems, 31, 8571\u20138580.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6356_CR31","unstructured":"Lee, J., Bahri, Y., Novak, R., Schoenholz, S. S., Pennington, J., & Sohl-Dickstein, J. (2018). Deep neural networks as Gaussian processes. In International conference on learning representations."},{"key":"6356_CR32","doi-asserted-by":"publisher","first-page":"124002","DOI":"10.1088\/1742-5468\/abc62b","volume":"12","author":"J Lee","year":"2020","unstructured":"Lee, J., Xiao, L., Schoenholz, S. S., Bahri, Y., Novak, R., Sohl-Dickstein, J., & Pennington, J. (2020). Wide neural networks of any depth evolve as linear models under gradient descent. Journal of Statistical Mechanics: Theory and Experiment, 12, 124002.","journal-title":"Journal of Statistical Mechanics: Theory and Experiment"},{"key":"6356_CR33","unstructured":"Li, T., Tan, L., Tao, Q., Liu, Y., & Huang, X. (2023).  Low Dimensional Trajectory Hypothesis is True: DNNs can be Trained in Tiny Subspaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45, 3411\u20133420, 2023"},{"key":"6356_CR34","first-page":"8157","volume":"31","author":"Y Li","year":"2018","unstructured":"Li, Y., & Liang, Y. (2018). Learning overparameterized neural networks via stochastic gradient descent on structured data. Advances in Neural Information Processing Systems, 31, 8157\u20138166.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6356_CR35","unstructured":"Li, Z., Wang, R., Yu, D., Du, S. S., Hu, W., Salakhutdinov, R., & Arora, S. (2019). Enhanced convolutional neural tangent kernels. arXiv preprint arXiv:1911.00809"},{"issue":"208","key":"6356_CR36","first-page":"1","volume":"21","author":"F Liu","year":"2020","unstructured":"Liu, F., Huang, X., Gong, C., Yang, J., & Li, L. (2020). Learning data-adaptive non-parametric kernels. Journal of Machine Learning Research, 21(208), 1\u201339.","journal-title":"Journal of Machine Learning Research"},{"key":"6356_CR37","unstructured":"Liu, L., Jiang, H., He, P., Chen, W., Liu, X., Gao, J., & Han, J. (2020b). On the variance of the adaptive learning rate and beyond. In ICLR 2020: Eighth international conference on learning representations."},{"key":"6356_CR38","unstructured":"Novak, R., Xiao, L., Lee, J., Bahri, Y., Yang, G., Hron, J., Abolafia, D. A., Pennington, J., & Sohl-Dickstein, J. (2019). Bayesian deep convolutional networks with many channels are Gaussian processes. In International conference on learning representations."},{"key":"6356_CR39","unstructured":"Samarin, M., Roth, V., & Belius, D. (2020). On the empirical neural tangent kernel of standard finite-width convolutional neural network architectures. arXiv preprint arXiv:2006.13645"},{"key":"6356_CR40","unstructured":"Shankar, V., Fang, A., Guo, W., Fridovich-Keil, S., Ragan-Kelley, J., Schmidt, L., & Recht, B. (2020). Neural kernels without tangents. In ICML 2020: 37th international conference on machine learning (vol.\u00a01, pp. 8614\u20138623)."},{"key":"6356_CR41","unstructured":"Sohl-Dickstein, J., Novak, R., Schoenholz, S. S., & Lee, J. (2020). On the infinite width limit of neural networks with a standard parameterization. arXiv preprint arXiv:2001.07301"},{"issue":"57","key":"6356_CR42","first-page":"1531","volume":"7","author":"S Sonnenburg","year":"2006","unstructured":"Sonnenburg, S., R\u00e4tsch, G., Sch\u00e4fer, C., & Sch\u00f6lkopf, B. (2006). Large scale multiple kernel learning. Journal of Machine Learning Research, 7(57), 1531\u20131565.","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"6356_CR43","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(1), 1929\u20131958.","journal-title":"Journal of Machine Learning Research"},{"key":"6356_CR44","unstructured":"Sutskever, I., Martens, J., Dahl, G., & Hinton, G. (2013). On the importance of initialization and momentum in deep learning. In Proceedings of the 30th international conference on machine learning (pp. 1139\u20131147)."},{"key":"6356_CR45","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.neunet.2018.01.016","volume":"101","author":"T Takase","year":"2018","unstructured":"Takase, T., Oyama, S., & Kurihara, M. (2018). Effective neural network training with adaptive learning rate based on training loss. Neural Networks, 101, 68\u201378.","journal-title":"Neural Networks"},{"key":"6356_CR46","unstructured":"Wei, C., Lee, J. D., Liu, Q., & Ma, T. (2019). Regularization matters: Generalization and optimization of neural nets v.s. their induced kernel. In 33rd Annual conference on neural information processing systems, NeurIPS 2019 (vol.\u00a032, pp. 9712\u20139724)."},{"key":"6356_CR47","first-page":"295","volume":"9","author":"CKI Williams","year":"1996","unstructured":"Williams, C. K. I. (1996). Computing with infinite networks. Advances in Neural Information Processing Systems, 9, 295\u2013301.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6356_CR48","unstructured":"Yang, G. (2019). Scaling limits of wide neural networks with weight sharing: Gaussian process behavior, gradient independence, and neural tangent kernel derivation. arXiv preprint arXiv:1902.04760"},{"key":"6356_CR49","unstructured":"Zeiler, M. D. (2012). Adadelta: An adaptive learning rate method. arXiv preprint arXiv:1212.5701"},{"key":"6356_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, Z. (2018). Improved Adam optimizer for deep neural networks. In 2018 IEEE\/ACM 26th international symposium on quality of service (IWQoS) (pp. 1\u20132).","DOI":"10.1109\/IWQoS.2018.8624183"},{"issue":"36","key":"6356_CR51","first-page":"1313","volume":"12","author":"J Zhuang","year":"2011","unstructured":"Zhuang, J., Tsang, I. W., & Hoi, S. C. H. (2011). A family of simple non-parametric kernel learning algorithms. Journal of Machine Learning Research, 12(36), 1313\u20131347.","journal-title":"Journal of Machine Learning Research"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06356-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-023-06356-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06356-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,20]],"date-time":"2024-07-20T00:04:41Z","timestamp":1721433881000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-023-06356-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,20]]},"references-count":51,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["6356"],"URL":"https:\/\/doi.org\/10.1007\/s10994-023-06356-3","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,20]]},"assertion":[{"value":"21 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 July 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Authors declare that they have no conflict of interest.","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"}]}}