{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T08:04:27Z","timestamp":1784189067393,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":15,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234165","type":"print"},{"value":"9789819234172","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-3417-2_48","type":"book-chapter","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T07:12:27Z","timestamp":1784185947000},"page":"564-574","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Do Nonlinear Transformers Implement Kernel Regression In-Context? An Empirical Investigation"],"prefix":"10.1007","author":[{"given":"Jiahui","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"48_CR1","unstructured":"Aky\u00fcrek, E., Schuurmans, D., Andreas, J., Ma, T., Zhou, D.: What learning algorithm is in-context learning? investigations with linear models. ArXiv abs\/2211.15661 (2022)."},{"key":"48_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2025.100886","volume":"60","author":"A Ali","year":"2026","unstructured":"Ali, A., Sharafian, A., Naeem, H.M.Y., Zakarya, M., Wu, Z., Bai, X.: Advanced computational models for urban traffic flow prediction: a comprehensive review and future directions. Comput Sci Rev. 60, 100886 (2026)","journal-title":"Comput Sci Rev"},{"key":"48_CR3","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/j.neunet.2021.10.021","volume":"145","author":"A Ali","year":"2022","unstructured":"Ali, A., Zhu, Y., Zakarya, M.: Exploiting dynamic spatio-temporal graph convolutional neural networks for citywide traffic flows prediction. Neural Netw. 145, 233\u2013247 (2022)","journal-title":"Neural Netw."},{"key":"48_CR4","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. ArXiv abs\/2005.14165 (2020)."},{"key":"48_CR5","doi-asserted-by":"crossref","unstructured":"Garg, S., Tsipras, D., Liang, P., Valiant, G.: What can transformers learn in-context? a case study of simple function classes. ArXiv abs\/2208.01066 (2022).","DOI":"10.52202\/068431-2217"},{"key":"48_CR6","unstructured":"Jacot, A., Gabriel, F., Hongler, C.: Neural tangent kernel: Convergence and generalization in neural networks. ArXiv abs\/1806.07572 (2018)."},{"key":"48_CR7","volume-title":"Transformers Are Rnns: Fast Autoregressive Transformers with Linear Attention","author":"A Katharopoulos","year":"2020","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N., Fleuret, F.: Transformers Are Rnns: Fast Autoregressive Transformers with Linear Attention. (2020)."},{"key":"48_CR8","doi-asserted-by":"crossref","unstructured":"Kim, J., Nakamaki, T., Suzuki, T.: Transformers are minimax optimal nonparametric in-context learners. ArXiv abs\/2408.12186 (2024).","DOI":"10.52202\/079017-3387"},{"key":"48_CR9","volume-title":"How Do Nonlinear Transformers Learn and Generalize in in-Context Learning?","author":"H Li","year":"2024","unstructured":"Li, H., Wang, M., Lu, S., Cui, X., Chen, P.Y.: How Do Nonlinear Transformers Learn and Generalize in in-Context Learning? (2024)."},{"key":"48_CR10","unstructured":"Mainali, N., Teixeira, L.: Exact learning dynamics of in-context learning in linear transformers and its application to non-linear transformers. ArXiv abs\/2504.12916 (2025)."},{"key":"48_CR11","unstructured":"Sander, M.E., Giryes, R., Suzuki, T., Blondel, M., Peyr\u00e9, G.: How do transformers perform in-context autoregressive learning? ArXiv abs\/2402.05787 (2024)."},{"key":"48_CR12","unstructured":"Shen, Z., Hsu, A., Lai, R., Liao, W.: Understanding in-context learning on structured manifolds: Bridging attention to kernel methods. ArXiv abs\/2506.10959 (2025)."},{"key":"48_CR13","volume-title":"On the Role of Transformer Feed-Forward Layers in Nonlinear in-Context Learning","author":"H Sun","year":"2025","unstructured":"Sun, H., Jadbabaie, A., Azizan, N.: On the Role of Transformer Feed-Forward Layers in Nonlinear in-Context Learning. (2025)."},{"key":"48_CR14","unstructured":"Tsai, Y.H.H., Bai, S., Yamada, M., Philippe Morency, L., Salakhutdinov, R.: Transformer dissection: An unified understanding for transformer\u2019s attention via the lens of kernel. ArXiv abs\/1908.11775 (2019)."},{"key":"48_CR15","doi-asserted-by":"crossref","unstructured":"Vladymyrov, M., von Oswald, J., Sandler, M., Ge, R.: Linear transformers are versatile in-context learners. ArXiv abs\/2402.14180 (2024).","DOI":"10.52202\/079017-1546"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3417-2_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T07:12:31Z","timestamp":1784185951000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3417-2_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,17]]},"ISBN":["9789819234165","9789819234172"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3417-2_48","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,17]]},"assertion":[{"value":"17 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}