{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T13:17:31Z","timestamp":1769260651732,"version":"3.49.0"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CCF-2403391"],"award-info":[{"award-number":["CCF-2403391"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CCF-2443097"],"award-info":[{"award-number":["CCF-2443097"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tit.2025.3648262","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T18:45:17Z","timestamp":1766601917000},"page":"921-945","source":"Crossref","is-referenced-by-count":0,"title":["Characterizing Dependence of Samples Along the Langevin Dynamics and Algorithms via Contraction of \u03a6-Mutual Information"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7439-3845","authenticated-orcid":false,"given":"Jiaming","family":"Liang","sequence":"first","affiliation":[{"name":"Goergen Institute for Data Science and Artificial Intelligence and the Department of Computer Science, University of Rochester, Rochester, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6597-2857","authenticated-orcid":false,"given":"Siddharth","family":"Mitra","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Yale University, New Haven, CT, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5679-9198","authenticated-orcid":false,"given":"Andre","family":"Wibisono","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Yale University, New Haven, CT, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/9780429258411"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.83.943"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-444-53548-1.50003-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1201\/b14835"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.1998.10480547"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1201\/b14835-6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1201\/b10905-2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1090\/mbk\/107"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1215\/kjm\/1250283556"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2549542"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1561\/0400000003"},{"key":"ref12","volume-title":"Log-Concave Sampling","author":"Chewi","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4132-4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1214\/aoap\/1026915617"},{"key":"ref15","first-page":"2422","article-title":"Convergence of Gaussian-smoothed optimal transport distance with sub-gamma distributions and dependent samples","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Zhang"},{"key":"ref16","first-page":"2299","article-title":"Estimating information flow in deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goldfeld"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71050-9"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1142\/S0218202518500574"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10955-019-02339-8"},{"key":"ref20","first-page":"678","article-title":"Further and stronger analogy between sampling and optimization: Langevin Monte Carlo and gradient descent","volume-title":"Proc. Conf. Learn. Theory","author":"Dalalyan"},{"key":"ref21","first-page":"186","article-title":"Convergence of Langevin MCMC in KL-divergence","volume-title":"Proc. Algorithmic Learn. Theory","author":"Cheng"},{"issue":"73","key":"ref22","first-page":"1","article-title":"Analysis of Langevin Monte Carlo via convex optimization","volume":"20","author":"Durmus","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref23","first-page":"8094","article-title":"Rapid convergence of the unadjusted Langevin algorithm: Isoperimetry suffices","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Vempala"},{"key":"ref24","first-page":"846","article-title":"Fast convergence of \u03a6-divergence along the unadjusted Langevin algorithm and proximal sampler","volume-title":"Proc. 36th Int. Conf. Algorithmic Learn. Theory","author":"Mitra"},{"key":"ref25","first-page":"2993","article-title":"Structured logconcave sampling with a restricted Gaussian Oracle","volume-title":"Proc. Conf. Learn. Theory","author":"Lee"},{"key":"ref26","first-page":"2984","article-title":"Improved analysis for a proximal algorithm for sampling","volume-title":"Proc. Conf. Learn. Theory","author":"Chen"},{"key":"ref27","first-page":"5754","article-title":"On a class of Gibbs sampling over networks","volume-title":"Proc. Thirty 6th Conf. Learn. Theory","author":"Yuan"},{"key":"ref28","first-page":"1473","article-title":"Improved dimension dependence of a proximal algorithm for sampling","volume-title":"Proc. Thirty 6th Annu. Conf. Learn. Theory","author":"Fan"},{"key":"ref29","volume-title":"Information Theory: From Coding to Learning","author":"Polyanskiy","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-7005-6_7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2603151"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-00227-9"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-9958(59)90348-1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2025.3548961"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.matpur.2010.02.004"},{"issue":"1","key":"ref36","first-page":"1","article-title":"Large-time behavior in non-symmetric fokker-Planck equations","volume":"6","author":"Achleitner","year":"2015","journal-title":"Rivista di Matematica della Universit di Parma"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.2307\/3318418"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00123"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12183"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1214\/16-AAP1238"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-024-09667-6"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1137\/24m1638689"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WSC57314.2022.10015293"},{"key":"ref44","article-title":"A proximal algorithm for sampling","author":"Liang","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3440"},{"key":"ref46","first-page":"4205","article-title":"The sample complexity of simple binary hypothesis testing","volume-title":"Proc. 37th Conf. Learn. Theory","author":"Pensia"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-7152(01)00172-9"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87987-9_18"},{"key":"ref49","first-page":"32680","article-title":"Robust \u03a6-divergence MDPs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ho"},{"key":"ref50","first-page":"39324","article-title":"Model-free robust \u03a6-divergence reinforcement learning using both offline and online data","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Panaganti"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.69.056111"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.0009-08.2008"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT45174.2021.9517999"},{"key":"ref54","first-page":"3474","article-title":"E\u03b3-mixing time","volume-title":"Proc. IEEE Int. Symp. Inf. Theory (ISIT)","author":"Zamanlooy"},{"key":"ref55","article-title":"f-MICL: Understanding and generalizing InfoNCE-based contrastive learning","author":"Lu","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT44484.2020.9174117"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/18.669153"},{"key":"ref58","article-title":"On maximal correlation, hypercontractivity, and the data processing inequality studied by erkip and cover","author":"Anantharam","year":"2013","journal-title":"arXiv:1304.6133"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-8162-8_8"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1214\/154957805100000104"},{"key":"ref61","article-title":"For how many iterations should we run Markov chain Monte Carlo?","author":"Margossian","year":"2023","journal-title":"arXiv:2311.02726"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1214\/24-BA1453"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.844072"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2172572"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8007014"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT63088.2025.11195365"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2018.8437454"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.23919\/ISITA.2018.8664285"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT63088.2025.11195302"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1137\/S0036141096303359"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/058"},{"key":"ref72","first-page":"2524","article-title":"Information-theoretic analysis of generalization capability of learning algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Xu"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3717823.3718202"},{"key":"ref74","article-title":"Proximal Oracles for optimization and sampling","author":"Liang","year":"2024","journal-title":"arXiv:2404.02239"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3653446"},{"key":"ref76","first-page":"2041","article-title":"The query complexity of sampling from strongly log-concave distributions in one dimension","volume-title":"Proc. Conf. Learn. Theory","author":"Chewi"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s00440-022-01158-5"},{"key":"ref78","first-page":"3264","article-title":"Efficiently learning and sampling multimodal distributions with data-based initialization","volume-title":"Proc. Conf. Learn. Theory","author":"Koehler"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.3150\/21-BEJ1450"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/S0021-7824(01)01208-9"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2024.3475290"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/S0021-7824(01)01207-7"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1214\/14-SS107"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1965.1053768"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/18\/11361350\/11314867-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/18\/11361350\/11314867.pdf?arnumber=11314867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T20:57:58Z","timestamp":1769201878000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11314867\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":85,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tit.2025.3648262","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"value":"0018-9448","type":"print"},{"value":"1557-9654","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}