{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T09:54:57Z","timestamp":1740131697121,"version":"3.37.3"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF Transdisciplinary Research in Principles of Data Science","award":["CCF-1934568"],"award-info":[{"award-number":["CCF-1934568"]}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["DMS-2053918"],"award-info":[{"award-number":["DMS-2053918"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["2019-06167"],"award-info":[{"award-number":["2019-06167"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Connaught New Researcher Award"},{"DOI":"10.13039\/100007631","name":"Canadian Institute for Advanced Research (CIFAR), Artificial Intelligence (AI) Chairs Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007631","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CIFAR AI Catalyst Grant"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/tit.2023.3318152","type":"journal-article","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T17:39:01Z","timestamp":1695317941000},"page":"571-593","source":"Crossref","is-referenced-by-count":0,"title":["An Analysis of Transformed Unadjusted Langevin Algorithm for Heavy-Tailed Sampling"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4686-8449","authenticated-orcid":false,"given":"Ye","family":"He","sequence":"first","affiliation":[{"name":"School of Mathematics, Georgia Institute of Technology, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5271-9314","authenticated-orcid":false,"given":"Krishnakumar","family":"Balasubramanian","sequence":"additional","affiliation":[{"name":"Department of Statistics, University of California at Davis, Davis, CA, USA"}]},{"given":"Murat A.","family":"Erdogdu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and the Department of Statistical Sciences, University of Toronto, Toronto, ON, Canada"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511550683"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9469.2007.00557.x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3150\/17-BEJ976"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1214\/lnms\/1196285623"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-01689-9","volume-title":"Computation of Multivariate Normal and TProbabilities","volume":"195","author":"Genz","year":"2009"},{"key":"ref6","first-page":"4810","article-title":"Non-asymptotic analysis of fractional Langevin Monte Carlo for non-convex optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nguyen"},{"key":"ref7","first-page":"8970","article-title":"Fractional underdamped Langevin dynamics: Retargeting SGD with momentum under heavy-tailed gradient noise","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"\u00b8Sim\u00b8sekli"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2307\/3318418"},{"journal-title":"Functional Inequal. Markov Semigroups and Spectral Theory","year":"2006","author":"Wang","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-00227-9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1214\/21-EJP643"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1214\/22-AOS2241"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12183"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1214\/16-AAP1238"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.spa.2019.02.016"},{"issue":"1","key":"ref16","first-page":"2666","article-title":"Analysis of Langevin Monte Carlo via convex optimization","volume":"20","author":"Durmus","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref17","first-page":"2565","article-title":"Logsmooth gradient concentration and tighter run-times for metropolized Hamiltonian Monte Carlo","volume-title":"Proc. Conf. Learn. Theory","author":"Lee"},{"key":"ref18","first-page":"1","article-title":"Log-concave sampling: Metropolis-Hastings algorithms are fast","volume":"20","author":"Dwivedi","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref19","first-page":"2100","article-title":"The randomized midpoint method for logconcave sampling","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Shen"},{"key":"ref20","first-page":"1","article-title":"On the ergodicity, bias and asymptotic normality of randomized midpoint sampling method","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"He"},{"key":"ref21","first-page":"1","article-title":"Fast mixing of metropolized Hamiltonian Monte Carlo: Benefits of multi-step gradients","volume":"21","author":"Chen","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref22","first-page":"1260","article-title":"Optimal dimension dependence of the metropolis-adjusted Langevin algorithm","volume-title":"Proc. Conf. Learn. Theory","author":"Chewi"},{"issue":"1","key":"ref23","first-page":"12348","article-title":"Minimax mixing time of the metropolis-adjusted Langevin algorithm for log-concave sampling","volume":"23","author":"Wu","year":"2022","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"ref24","first-page":"10720","article-title":"Bounding the error of discretized Langevin algorithms for non-strongly log-concave targets","volume":"23","author":"Dalalyan","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref25","article-title":"The Langevin Monte Carlo algorithm in the non-smooth logconcave case","author":"Lehec","year":"2021","journal-title":"arXiv:2101.10695"},{"key":"ref26","article-title":"Sharp convergence rates for Langevin dynamics in the nonconvex setting","author":"Cheng","year":"2018","journal-title":"arXiv:1805.01648"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1820003116"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1214\/19-AAP1535"},{"key":"ref29","first-page":"8094","article-title":"Rapid convergence of the unadjusted Langevin algorithm: Isoperimetry suffices","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vempala"},{"key":"ref30","first-page":"1776","article-title":"On the convergence of Langevin Monte Carlo: The interplay between tail growth and smoothness","volume-title":"Proc. Conf. Learn. Theory","author":"Erdogdu"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1214\/22-BJPS538"},{"key":"ref32","first-page":"1","article-title":"Analysis of Langevin Monte Carlo from Poincar\u00e9 to log-Sobolev","volume-title":"Proc. Conf. Learn. Theory","author":"Chewi"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0107213"},{"key":"ref34","first-page":"3200","article-title":"Fractional Langevin Monte Carlo: Exploring L\u00e9vy driven stochastic differential equations for Markov Chain Monte Carlo","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"\u00b8Sim\u00b8sekli"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3150\/20-BEJ1300"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1214\/12-AOS1048"},{"key":"ref37","article-title":"Stereographic Markov chain Monte Carlo","author":"Yang","year":"2022","journal-title":"arXiv:2205.12112"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1214\/18-AOS1714"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1214\/19-AAP1552"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1214\/18-AAP1453"},{"key":"ref41","first-page":"9694","article-title":"Global non-convex optimization with discretized diffusions","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Erdogdu"},{"key":"ref42","first-page":"7748","article-title":"Stochastic Runge\u2013Kutta accelerates Langevin Monte Carlo and beyond","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Li"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1214\/12-AIHP537"},{"issue":"1","key":"ref44","first-page":"2639","article-title":"Inference via low-dimensional couplings","volume":"19","author":"Spantini","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1137\/15M1032478"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-021-09537-5"},{"key":"ref47","first-page":"1","article-title":"Coupling-based invertible neural networks are universal diffeomorphism approximators","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Teshima"},{"key":"ref48","first-page":"5628","article-title":"Representational aspects of depth and conditioning in normalizing flows","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koehler"},{"issue":"57","key":"ref49","first-page":"1","article-title":"Normalizing flows for probabilistic modeling and inference","volume":"22","author":"Papamakarios","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref50","article-title":"Accelerating Langevin sampling with birthdeath","author":"Lu","year":"2019","journal-title":"arXiv:1905.09863"},{"key":"ref51","first-page":"4672","article-title":"A nonasymptotic analysis for stein variational gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Korba"},{"key":"ref52","article-title":"A finite-particle convergence rate for stein variational gradient descent","author":"Shi","year":"2022","journal-title":"arXiv:2211.09721"},{"key":"ref53","article-title":"Towards understanding the dynamics of Gaussian-stein variational gradient descent","author":"Liu","year":"2023","journal-title":"arXiv:2305.14076"},{"key":"ref54","article-title":"Provably fast finite particle variants of SVGD via virtual particle stochastic approximation","author":"Das","year":"2023","journal-title":"arXiv:2305.17558"},{"issue":"5","key":"ref55","doi-asserted-by":"crossref","first-page":"1279","DOI":"10.1023\/A:1018623930325","article-title":"On the trend to equilibrium for some dissipative systems with slowly increasing a priori bounds","volume":"98","author":"Toscani","year":"2000","journal-title":"J. Stat. Phys."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1515\/fca-2017-0002"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1006\/jfan.2001.3776"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-1236(03)00165-4"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1214\/EJP.v15-754"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1051\/ps\/2013048"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s10959-013-0500-5"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1006\/jfan.1996.3007"},{"key":"ref63","first-page":"1","article-title":"Towards a complete analysis of Langevin Monte Carlo: Beyond Poincar\u00e9 inequality","volume-title":"Proc. 36th Conf. Learn. Theory","volume":"195","author":"Mousavi-Hosseini"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS57990.2023.00131"},{"key":"ref65","first-page":"375","article-title":"Fisher information lower bounds for sampling","volume-title":"Proc. Int. Conf. Algorithmic Learn. Theory","author":"Chewi"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfa.2007.11.002"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/BF01011161"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0075847"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/18\/10375320\/10258391-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/18\/10375320\/10258391.pdf?arnumber=10258391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T04:13:39Z","timestamp":1705032819000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10258391\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":68,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tit.2023.3318152","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"type":"print","value":"0018-9448"},{"type":"electronic","value":"1557-9654"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}