{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:42:54Z","timestamp":1773376974511,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"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":[[2025,6,22]]},"DOI":"10.1109\/isit63088.2025.11195663","type":"proceedings-article","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T17:48:08Z","timestamp":1760982488000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Coupling Without Communication and Drafter-Invariant Speculative Decoding"],"prefix":"10.1109","author":[{"given":"Majid","family":"Daliri","sequence":"first","affiliation":[{"name":"New York University"}]},{"given":"Christopher","family":"Musco","sequence":"additional","affiliation":[{"name":"New York University"}]},{"given":"Ananda Theertha","family":"Suresh","sequence":"additional","affiliation":[{"name":"Google Research,NY"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4086\/toc.2020.v016a012"},{"key":"ref2","article-title":"Information-theoretic methods for highdimensional statistics","author":"Wu","year":"2020","journal-title":"Lecture notes, Yale University, New Haven, CT"},{"key":"ref3","volume-title":"Consistent weighted sampling","author":"Manasse","year":"2010"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/585265.585268"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.4086\/toc.2009.v005a008"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.80"},{"key":"ref7","article-title":"Simple and efficient weighted minwise hashing","author":"Shrivastava","year":"2016","journal-title":"Advances in Neural Information Processing Systems 29 (NeurIPS)"},{"key":"ref8","article-title":"DartMinHash: Fast sketching for weighted sets","author":"Christiani","year":"2020","journal-title":"arXiv"},{"key":"ref9","article-title":"Fast inference from transformers via speculative decoding","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML)","author":"Leviathan"},{"key":"ref10","article-title":"Accelerating large language model decoding with speculative sampling","author":"Chen","year":"2023","journal-title":"arXiv"},{"key":"ref11","article-title":"SpecTr: Fast speculative decoding via optimal transport","author":"Sun","year":"2023","journal-title":"Advances in Neural Information Processing Systems 36 (NeurIPS)"},{"key":"ref12","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022","journal-title":"Advances in Neural Information Processing Systems 35 (NeurIPS)"},{"key":"ref13","article-title":"A survey on efficient inference for large language models","author":"Zhou","year":"2024","journal-title":"arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1534"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-3758(96)00185-1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3584372.3589935"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3618260.3649744"},{"key":"ref18","first-page":"3499","article-title":"Stochastic beams and where to find them: The gumbel-top-k trick for sampling sequences without replacement","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML)","author":"Kool"},{"key":"ref19","first-page":"3086","article-title":"A* sampling","author":"Maddison","year":"2014","journal-title":"Advances in Neural Information Processing Systems 27 (NeurIPS)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3157042"},{"key":"ref21","article-title":"Coupling without communication and drafter-invariant speculative decoding","author":"Daliri","year":"2024","journal-title":"arXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8006596"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CCC.2007.32"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3021067"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipl.2005.11.003"},{"key":"ref26","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv"},{"key":"ref27","article-title":"OpenAI","year":"2023","journal-title":"GPT-4 technical report"},{"key":"ref28","article-title":"Gemini Team, Google","year":"2023","journal-title":"Gemini: a family of highly capable multimodal models"},{"key":"ref29","article-title":"Gemma Team, Google","year":"2024","journal-title":"Gemma 2: Improving open language models at a practical size"}],"event":{"name":"2025 IEEE International Symposium on Information Theory (ISIT)","location":"Ann Arbor, MI, USA","start":{"date-parts":[[2025,6,22]]},"end":{"date-parts":[[2025,6,27]]}},"container-title":["2025 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11195206\/11195207\/11195663.pdf?arnumber=11195663","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:29:42Z","timestamp":1773347382000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11195663\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/isit63088.2025.11195663","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}