{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T23:05:53Z","timestamp":1779923153050,"version":"3.53.1"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032214799","type":"print"},{"value":"9783032214805","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-21480-5_9","type":"book-chapter","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T22:29:43Z","timestamp":1779920983000},"page":"120-137","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Operator-Based Generalization Bound for\u00a0Deep Learning: Insights on Multi-task Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4811-6585","authenticated-orcid":false,"given":"Mahdi","family":"Mohammadigohari","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3096-2844","authenticated-orcid":false,"given":"Giuseppe","family":"Di Fatta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giuseppe","family":"Nicosia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Panos M.","family":"Pardalos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Argyriou, A., Evgeniou, T., Pontil, M.: Multi-task feature learning. In: Advances in Neural Information Processing Systems, vol.\u00a019 (2006)","DOI":"10.7551\/mitpress\/7503.003.0010"},{"key":"9_CR2","unstructured":"Bartlett, P.L., Foster, D.J., Telgarsky, M.J.: Spectrally-normalized margin bounds for neural networks. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), vol.\u00a031 (2017)"},{"issue":"48","key":"9_CR3","doi-asserted-by":"publisher","first-page":"30063","DOI":"10.1073\/pnas.1907378117","volume":"117","author":"PL Bartlett","year":"2020","unstructured":"Bartlett, P.L., Long, P.M., Lugosi, G., Tsigler, A.: Benign overfitting in linear regression. Proc. Natl. Acad. Sci. 117(48), 30063\u201330070 (2020)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"9_CR4","unstructured":"Bietti, A., Mialon, G., Chen, D., Mairal, J.: A kernel perspective for regularizing deep neural networks. In: Proceedings of the 36th International Conference on Machine Learning (ICML) (2019)"},{"issue":"64","key":"9_CR5","first-page":"1","volume":"20","author":"B Bohn","year":"2019","unstructured":"Bohn, B., Griebel, M., Rieger, C.: A representer theorem for deep kernel learning. J. Mach. Learn. Res. 20(64), 1\u201332 (2019)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"9_CR6","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/s10208-006-0196-8","volume":"7","author":"A Caponnetto","year":"2007","unstructured":"Caponnetto, A., Vito, E.D.: Optimal rates for the regularized least-squares algorithm. Found. Comput. Math. 7(3), 331\u2013368 (2007)","journal-title":"Found. Comput. Math."},{"key":"9_CR7","unstructured":"Chen, L., Xu, S.: Deep neural tangent kernel and laplace kernel have the same RKHS. In: In Proceedings of the 9th International Conference on Learning Representations (ICLR) (2021)"},{"key":"9_CR8","unstructured":"Collins, L., Hassani, H., Soltanolkotabi, M., Mokhtari, A., Shakkottai, S.: Provable multi-task representation learning by two-layer relu neural networks. In: Proceedings of the Forty-First International Conference on Machine Learning (2024)"},{"key":"9_CR9","unstructured":"Crawshaw, M.: Multi-task learning with deep neural networks: a survey. arXiv preprint arXiv:2009.09796 (2020)"},{"key":"9_CR10","unstructured":"El\u00a0Ahmad, T., Laforgue, P., d\u2019Alch\u00e9 Buc, F.: Fast kernel methods for generic Lipschitz losses via p-sparsified sketches. Trans. Mach. Learn. Res. (2023)"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Fatta, G.D., Nicosia, G., Ojha, V., Pardalos, P.: Multi-task deep learning as multi-objective optimization. In: Encyclopedia of Optimization, pp. 1\u201310. Springer (2023)","DOI":"10.1007\/978-3-030-54621-2_827-1"},{"key":"9_CR12","unstructured":"Golowich, N., Rakhlin, A., Shamir, O.: Size-independent sample complexity of neural networks. In: Proceedings of the 2018 Conference on Learning Theory (COLT) (2018)"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Golowich, N., Rakhlin, A., Shamir, O.: Size-independent sample complexity of neural networks. Inf. Inference J. IMA 9(2), 473\u2013504 (2020)","DOI":"10.1093\/imaiai\/iaz007"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Hashimoto, Y., Ikeda, M., Kadri, H.: Deep learning with kernels through RKHM and the perron-frobenius operator. In: Advances in Neural Information Processing Systems, vol.\u00a036, pp. 50677\u201350696 (2023)","DOI":"10.52202\/075280-2205"},{"key":"9_CR15","unstructured":"Hashimoto, Y., Sonoda, S., Ishikawa, I., Nitanda, A., Suzuki, T.: Koopman-based generalization bound: New aspect for full-rank weights. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=JN7TcCm9LF"},{"issue":"24","key":"9_CR16","first-page":"1","volume":"22","author":"R Huusari","year":"2021","unstructured":"Huusari, R., Kadri, H.: Entangled kernels - beyond separability. J. Mach. Learn. Res. 22(24), 1\u201340 (2021)","journal-title":"J. Mach. Learn. Res."},{"key":"9_CR17","unstructured":"Jacot, A., Gabriel, F., Hongler, C.: Neural tangent kernel: convergence and generalization in neural networks. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), vol.\u00a031 (2018)"},{"key":"9_CR18","unstructured":"Ju, H., Li, D., Zhang, H.R.: Robust fine-tuning of deep neural networks with Hessian-based generalization guarantees. In: Proceedings of the 39th International Conference on Machine Learning (ICML) (2022)"},{"key":"9_CR19","unstructured":"Laforgue, P., Cl\u00e9men\u00e7on, S., d\u2019Alch\u00e9 Buc, F.: Autoencoding any data through kernel autoencoders. In: Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS) (2019)"},{"key":"9_CR20","unstructured":"Li, Z., Meunier, D., Mollenhauer, M., Gretton, A.: Towards optimal sobolev norm rates for the vector-valued regularized least-squares algorithm. J. Mach. Learn. Res. 25(181), 1\u201351 (2024). http:\/\/jmlr.org\/papers\/v25\/23-1663.html"},{"issue":"108","key":"9_CR21","first-page":"1","volume":"22","author":"Z Li","year":"2021","unstructured":"Li, Z., Ton, J.F., Oglic, D., Sejdinovic, D.: Towards a unified analysis of random fourier features. J. Mach. Learn. Res. 22(108), 1\u201351 (2021)","journal-title":"J. Mach. Learn. Res."},{"key":"9_CR22","unstructured":"Lindsey, J.W., Lippl, S.: Implicit regularization of multi-task learning and finetuning in overparameterized neural networks. arXiv preprint arXiv:2310.02396 (2023)"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Mahoney, M.W., et\u00a0al.: Randomized algorithms for matrices and data. Found. Trends\u00ae Mach. Learn. 3(2), 123\u2013224 (2011)","DOI":"10.1561\/2200000035"},{"key":"9_CR24","unstructured":"Mairal, J., Koniusz, P., Harchaoui, Z., Schmid, C.: Convolutional kernel networks. In: Proceedings of the Advances in Neural Information Processing Systems (NIPS), vol.\u00a027 (2014)"},{"key":"9_CR25","unstructured":"Mallinar, N.R., Simon, J.B., Abedsoltan, A., Pandit, P., Belkin, M., Nakkiran, P.: Benign, tempered, or catastrophic: toward a refined taxonomy of overfitting. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), vol.\u00a037 (2022)"},{"key":"9_CR26","first-page":"117","volume":"7","author":"A Maurer","year":"2006","unstructured":"Maurer, A.: Bounds for linear multi-task learning. J. Mach. Learn. Res. 7, 117\u2013139 (2006)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"9_CR27","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1162\/0899766052530802","volume":"17","author":"CA Micchelli","year":"2005","unstructured":"Micchelli, C.A., Pontil, M.: On learning vector-valued functions. Neural Comput. 17(1), 177\u2013204 (2005)","journal-title":"Neural Comput."},{"key":"9_CR28","unstructured":"Mohammadigohari, M., Di\u00a0Fatta, G., Nicosia, G., Pardalos, P.: On the koopman-based generalization bounds for multi-task deep learning. In: Nicosia, G., et\u00a0al. (eds.) Proceedings of the International Conference on Learning and Discovery (LOD). Lecture Notes in Computer Science. Springer, Cham (2025, accepted)"},{"key":"9_CR29","unstructured":"Mohri, M., Rostamizadeh, A., Talwalkar, A.: Foundations of Machine Learning. MIT Press, Cambridge (2018)"},{"key":"9_CR30","unstructured":"Neyshabur, B., Tomioka, R., Srebro, N.: Norm-based capacity control in neural networks. In: Proceedings of the 2015 Conference on Learning Theory (COLT) (2015)"},{"key":"9_CR31","unstructured":"Ober, S.W., Rasmussen, C.E., van\u00a0der Wilk, M.: The promises and pitfalls of deep kernel learning. In: Proceedings of the 37th Conference on Uncertainty in Artificial Intelligence (UAI) (2021)"},{"key":"9_CR32","unstructured":"Pontil, M., Maurer, A.: Excess risk bounds for multitask learning with trace norm regularization. In: Proceedings of the Conference on Learning Theory, pp. 55\u201376. PMLR (2013)"},{"key":"9_CR33","unstructured":"Rudi, A., Rosasco, L.: Generalization properties of learning with random features. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 3215\u20133225 (2017)"},{"issue":"231","key":"9_CR34","first-page":"1","volume":"25","author":"J Shenouda","year":"2024","unstructured":"Shenouda, J., Parhi, R., Lee, K., Nowak, R.D.: Variation spaces for multi-output neural networks: insights on multi-task learning and network compression. J. Mach. Learn. Res. 25(231), 1\u201340 (2024)","journal-title":"J. Mach. Learn. Res."},{"key":"9_CR35","unstructured":"Sindhwani, V., Minh, H.Q., Lozano, A.C.: Scalable matrix-valued kernel learning for high-dimensional nonlinear multivariate regression and granger causality. In: Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence (UAI) (2013)"},{"key":"9_CR36","unstructured":"Suzuki, T., Abe, H., Nishimura, T.: Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural network. In: Proceedings of the 8th International Conference on Learning Representations (ICLR) (2020)"},{"key":"9_CR37","unstructured":"Wittwar, D.: Approximation with matrix-valued kernels and highly effective error estimators for reduced basis approximations. Ph.D. thesis, Universit\u00e4t Stuttgart, Stuttgart, Germany (2022)"},{"key":"9_CR38","doi-asserted-by":"crossref","unstructured":"Woodruff, D.P.: Sketching as a tool for numerical linear algebra. Found. Trends\u00ae Theor. Comput. Sci. 10(1-2), 1\u2013157 (2014)","DOI":"10.1561\/0400000060"},{"issue":"3","key":"9_CR39","doi-asserted-by":"publisher","first-page":"991","DOI":"10.1214\/16-AOS1472","volume":"45","author":"Y Yang","year":"2017","unstructured":"Yang, Y., Pilanci, M., Wainwright, M.J.: Randomized sketches for kernels: fast and optimal nonparametric regression. Ann. Stat. 45(3), 991\u20131023 (2017)","journal-title":"Ann. Stat."},{"issue":"1","key":"9_CR40","first-page":"1385","volume":"19","author":"N Yousefi","year":"2018","unstructured":"Yousefi, N., Lei, Y., Kloft, M., Mollaghasemi, M., Anagnostopoulos, G.C.: Local rademacher complexity-based learning guarantees for multi-task learning. J. Mach. Learn. Res. 19(1), 1385\u20131431 (2018)","journal-title":"J. Mach. Learn. Res."},{"key":"9_CR41","unstructured":"Zhang, H., Xu, Y., Zhang, Q.: Refinement of operator-valued reproducing kernels. J. Mach. Learn. Res. 13(4), 91\u2013136 (2012). http:\/\/jmlr.org\/papers\/v13\/zhang12a.html"}],"container-title":["Lecture Notes in Computer Science","Machine Learning, Optimization, and Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-21480-5_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T22:29:51Z","timestamp":1779920991000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-21480-5_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032214799","9783032214805"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-21480-5_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LOD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Artificial Intelligence Symposium","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Castiglione della Pescaia","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mod2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lod2025.icas.events","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}