{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T06:18:52Z","timestamp":1787725132681,"version":"build-2784847793"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/isit62367.2026.11653612","type":"proceedings-article","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T19:14:28Z","timestamp":1787685268000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["On the Generalization of Knowledge Distillation: An Information-Theoretic View"],"prefix":"10.1109","author":[{"given":"Bingying","family":"Li","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou)","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyun","family":"He","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou)","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098135"},{"key":"ref4","first-page":"5142","article-title":"Towards understanding knowledge distillation","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Phuong"},{"key":"ref5","article-title":"Do deep nets really need to be deep?","volume-title":"Advances in Neural Information Processing Systems","volume":"27","author":"Ba","year":"2014"},{"key":"ref6","article-title":"Unifying distillation and privileged information","volume-title":"International Conference on Learning Representations (ICLR)","author":"Lopez-Paz"},{"issue":"61","key":"ref7","first-page":"2023","article-title":"Learning using privileged information: Similarity control and knowledge transfer","volume-title":"Journal of Machine Learning Research","volume":"16","author":"Vapnik","year":"2015"},{"key":"ref8","article-title":"Generalization bounds via distillation","volume-title":"International Conference on Learning Representations","author":"Hsu"},{"key":"ref9","first-page":"7632","article-title":"A statistical perspective on distillation","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Menon"},{"key":"ref10","first-page":"75229","article-title":"Knowledge distillation performs partial variance reduction","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Safaryan","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"ref12","first-page":"20823","article-title":"Knowledge distillation in wide neural networks: Risk bound, data efficiency and imperfect teacher","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Ji","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.1.1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01932"},{"key":"ref15","article-title":"Sharpness-aware minimization for efficiently improving generalization","volume-title":"International Conference on Learning Representations","author":"Foret"},{"key":"ref16","first-page":"43012","article-title":"Leveraging flatness to improve information-theoretic generalization bounds for SGD","volume-title":"International Conference on Learning Representations","volume":"2025","author":"Peng"},{"key":"ref17","article-title":"The information bottleneck method","author":"Tishby","year":"2000"},{"key":"ref18","first-page":"607","article-title":"Efficient knowledge distillation from model checkpoints","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Wang","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00938"},{"key":"ref20","article-title":"Contrastive representation distillation","volume-title":"International Conference on Learning Representations","author":"Tian"},{"key":"ref21","first-page":"26722","article-title":"Bayes conditional distribution estimation for knowledge distillation based on conditional mutual information","volume-title":"International Conference on Learning Representations","volume":"2024","author":"Ye"},{"key":"ref22","article-title":"Supplementary material","author":"Li","year":"2026"},{"key":"ref23","article-title":"Information-theoretic analysis of generalization capability of learning algorithms","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Xu","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2025.3581715"},{"key":"ref25","first-page":"29321","article-title":"Drone: Data-aware low-rank compression for large NLP models","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Chen","year":"2021"}],"event":{"name":"2026 IEEE International Symposium on Information Theory (ISIT)","location":"Guangzhou, China","start":{"date-parts":[[2026,6,28]]},"end":{"date-parts":[[2026,7,3]]}},"container-title":["2026 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11653602\/11653603\/11653612.pdf?arnumber=11653612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T05:26:07Z","timestamp":1787721967000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11653612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/isit62367.2026.11653612","relation":{},"subject":[],"published":{"date-parts":[[2026,6]]}}}