{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:58:26Z","timestamp":1778605106911,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819681853","type":"print"},{"value":"9789819681860","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-8186-0_1","type":"book-chapter","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T10:17:44Z","timestamp":1750155464000},"page":"3-15","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Nested Zeroth-Order Fine-Tuning Approach for\u00a0Cloud-Edge LLM Agents"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4562-7654","authenticated-orcid":false,"given":"Ya","family":"Liu","sequence":"first","affiliation":[]},{"given":"Kai","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Keying","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Chengtao","family":"Jian","sequence":"additional","affiliation":[]},{"given":"Wuguang","family":"Ni","sequence":"additional","affiliation":[]},{"given":"Xiaozhou","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Ye","family":"Ouyang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"issue":"17","key":"1_CR1","doi-asserted-by":"publisher","first-page":"15435","DOI":"10.1109\/JIOT.2022.3176400","volume":"9","author":"P McEnroe","year":"2022","unstructured":"McEnroe, P., Wang, S., Liyanage, M.: A survey on the convergence of edge computing and AI for UAVs: opportunities and challenges. IEEE Internet Things J. 9(17), 15435\u201315459 (2022)","journal-title":"IEEE Internet Things J."},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Zhang, M., Cao, J., Shen, X., Cui, Z.: Edgeshard: efficient LLM inference via collaborative edge computing. arXiv preprint arXiv:2405.14371 (2024)","DOI":"10.1109\/JIOT.2024.3524255"},{"key":"1_CR3","volume-title":"LLM-based edge intelligence: a comprehensive survey on architectures, applications, security and trustworthiness","author":"O Friha","year":"2024","unstructured":"Friha, O., Ferrag, M.A., Kantarci, B., Cakmak, B., Ozgun, A., Ghoualmi-Zine, N.: LLM-based edge intelligence: a comprehensive survey on architectures, applications, security and trustworthiness. IEEE Open J. Commun, Soc (2024)"},{"key":"1_CR4","unstructured":"Zhang, Y., et\u00a0al.: Revisiting zeroth-order optimization for memory-efficient LLM fine-tuning: A benchmark. arXiv preprint arXiv:2402.11592 (2024)"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Yang, K., Wu, Y., Huang, J., Wang, X., Verd\u00fa, S.: Distributed robust optimization for communication networks. In: IEEE INFOCOM 2008-The 27th Conference on Computer Communications, pp. 1157\u20131165. IEEE (2008)","DOI":"10.1109\/INFOCOM.2008.171"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Hao, Z., Jiang, H., Jiang, S., Ren, J., Cao, T.: Hybrid SLM and LLM for edge-cloud collaborative inference. In: Proceedings of the Workshop on Edge and Mobile Foundation Models, pp. 36\u201341 (2024)","DOI":"10.1145\/3662006.3662067"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Thapa, C., Arachchige, P.C.M., Camtepe, S., Sun, L.: Splitfed: when federated learning meets split learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a036, pp. 8485\u20138493 (2022)","DOI":"10.1609\/aaai.v36i8.20825"},{"issue":"16","key":"1_CR8","doi-asserted-by":"publisher","first-page":"14285","DOI":"10.1109\/JIOT.2023.3243391","volume":"10","author":"Y Liu","year":"2023","unstructured":"Liu, Y., Zhou, Y., Yang, K., Wang, X.: Unsupervised deep learning for IoT time series. IEEE Internet Things J. 10(16), 14285\u201314306 (2023)","journal-title":"IEEE Internet Things J."},{"key":"1_CR9","unstructured":"OpenAI (2024). https:\/\/beta.openai.com\/docs\/guides\/fine-tuning"},{"key":"1_CR10","unstructured":"Li, H., et al.: Blade: enhancing black-box large language models with small domain-specific models. arXiv preprint arXiv:2403.18365 (2024)"},{"key":"1_CR11","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/s10898-015-0355-7","volume":"66","author":"V Gergel","year":"2016","unstructured":"Gergel, V., Grishagin, V., Gergel, A.: Adaptive nested optimization scheme for multidimensional global search. J. Glob. Optim. 66, 35\u201351 (2016)","journal-title":"J. Glob. Optim."},{"key":"1_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejco.2021.100007","volume":"9","author":"T Kleinert","year":"2021","unstructured":"Kleinert, T., Labb\u00e9, M., Ljubi\u0107, I., Schmidt, M.: A survey on mixed-integer programming techniques in bilevel optimization. EURO J. Comput. Optim. 9, 100007 (2021)","journal-title":"EURO J. Comput. Optim."},{"key":"1_CR13","unstructured":"Jiao, Y., Yang, K., Wu, T., Song, D., Jian, C.: Asynchronous distributed bilevel optimization. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"1_CR14","first-page":"7987","volume":"35","author":"Y Jiao","year":"2022","unstructured":"Jiao, Y., Yang, K., Song, D.: Distributed distributionally robust optimization with non-convex objectives. Adv. Neural. Inf. Process. Syst. 35, 7987\u20137999 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Jiao, Y., Yang, K., Wu, T., Jian, C., Huang, J.: Provably convergent federated trilevel learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 12928\u201312937 (2024)","DOI":"10.1609\/aaai.v38i11.29190"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Chen, X., Xiong, Y., Yang, K.: Robust beamforming for downlink multi-cell systems: a bilevel optimization perspective. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 7969\u20137977 (2024)","DOI":"10.1609\/aaai.v38i8.28634"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Chen, P.Y., Zhang, H., Sharma, Y., Yi, J., Hsieh, C.J.: Zoo: zeroth order optimization based black-box attacks to deep neural networks without training substitute models. In: Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security, pp. 15\u201326 (2017)","DOI":"10.1145\/3128572.3140448"},{"issue":"1","key":"1_CR18","first-page":"1616","volume":"23","author":"F Huang","year":"2022","unstructured":"Huang, F., Gao, S., Pei, J., Huang, H.: Accelerated zeroth-order and first-order momentum methods from mini to minimax optimization. J. Mach. Learn. Res. 23(1), 1616\u20131685 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR19","unstructured":"Chen, L., Xu, J., Zhang, J.: On bilevel optimization without lower-level strong convexity. arXiv preprint arXiv:2301.00712 (2023)"},{"issue":"5","key":"1_CR20","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/MSP.2020.3003837","volume":"37","author":"S Liu","year":"2020","unstructured":"Liu, S., Chen, P.Y., Kailkhura, B., Zhang, G., Hero, A.O., III., Varshney, P.K.: A primer on zeroth-order optimization in signal processing and machine learning: principals, recent advances, and applications. IEEE Signal Process. Mag. 37(5), 43\u201354 (2020)","journal-title":"IEEE Signal Process. Mag."},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Boyd, S., Boyd, S.P., Vandenberghe, L.: Convex optimization. Cambridge university press (2004)","DOI":"10.1017\/CBO9780511804441"},{"key":"1_CR22","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/s11081-012-9198-y","volume":"15","author":"K Yang","year":"2014","unstructured":"Yang, K., Huang, J., Wu, Y., Wang, X., Chiang, M.: Distributed robust optimization (DRO), part I: framework and example. Optim. Eng. 15, 35\u201367 (2014)","journal-title":"Optim. Eng."},{"key":"1_CR23","first-page":"53038","volume":"36","author":"S Malladi","year":"2023","unstructured":"Malladi, S., et al.: Fine-tuning language models with just forward passes. Adv. Neural. Inf. Process. Syst. 36, 53038\u201353075 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR24","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"1_CR25","unstructured":"Mitra, A., Khanpour, H., Rosset, C., Awadallah, A.: Orca-math: unlocking the potential of SLMs in grade school math. arXiv preprint arXiv:2402.14830 (2024)"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Yuan, Q., Kazemi, M., Xu, X., Noble, I., Imbrasaite, V., Ramachandran, D.: Tasklama: probing the complex task understanding of language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 19468\u201319476 (2024)","DOI":"10.1609\/aaai.v38i17.29918"},{"key":"1_CR27","unstructured":"Zhao, W., Shang, M., Liu, Y., Wang, L., Liu, J.: Ape210k: a large-scale and template-rich dataset of math word problems. arXiv preprint arXiv:2009.11506 (2020)"},{"key":"1_CR28","doi-asserted-by":"publisher","unstructured":"Axelbrooke, S.: Customer support on twitter (2017). https:\/\/doi.org\/10.34740\/KAGGLE\/DSV\/8841. https:\/\/www.kaggle.com\/dsv\/8841","DOI":"10.34740\/KAGGLE\/DSV\/8841"},{"key":"1_CR29","first-page":"22199","volume":"35","author":"T Kojima","year":"2022","unstructured":"Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. Adv. Neural. Inf. Process. Syst. 35, 22199\u201322213 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR30","unstructured":"Yang, C., et al.: Large language models as optimizers. In: The Twelfth International Conference on Learning Representations"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8186-0_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T11:02:41Z","timestamp":1750158161000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8186-0_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819681853","9789819681860"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8186-0_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"18 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}