{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T14:53:03Z","timestamp":1776955983536,"version":"3.51.4"},"reference-count":81,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T00:00:00Z","timestamp":1721952000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T00:00:00Z","timestamp":1721952000000},"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":["Found Comput Math"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s10208-024-09667-6","type":"journal-article","created":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T20:02:04Z","timestamp":1722024124000},"page":"1345-1395","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Analysis of Langevin Monte Carlo from Poincar\u00e9 to Log-Sobolev"],"prefix":"10.1007","volume":"25","author":[{"given":"Sinho","family":"Chewi","sequence":"first","affiliation":[]},{"given":"Murat A.","family":"Erdogdu","sequence":"additional","affiliation":[]},{"given":"Mufan","family":"Li","sequence":"additional","affiliation":[]},{"given":"Ruoqi","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Matthew S.","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,7,26]]},"reference":[{"key":"9667_CR1","doi-asserted-by":"crossref","unstructured":"A. Arnold, P. Markowich, G. Toscani, and A. Unterreiter. \u201cOn convex Sobolev inequalities and the rate of convergence to equilibrium for Fokker\u2013Planck type equations\u201d. In: Comm. Partial Differential Equations 26.1-2 (2001), pp.\u00a043\u2013100.","DOI":"10.1081\/PDE-100002246"},{"key":"9667_CR2","doi-asserted-by":"crossref","unstructured":"D. Bakry, I. Gentil, and M. Ledoux. Analysis and geometry of Markov diffusion operators. Vol.\u00a0348. Grundlehren der Mathematischen Wissenschaften [Fundamental Principles of Mathematical Sciences]. Springer, Cham, (2014), pp.\u00a0xx+552.","DOI":"10.1007\/978-3-319-00227-9"},{"key":"9667_CR3","doi-asserted-by":"crossref","unstructured":"J.-B. Bardet, N. Gozlan, F. Malrieu, and P.-A. Zitt. \u201cFunctional inequalities for Gaussian convolutions of compactly supported measures: explicit bounds and dimension dependence\u201d. In: Bernoulli 24.1 (2018), pp.\u00a0333\u2013353.","DOI":"10.3150\/16-BEJ879"},{"key":"9667_CR4","doi-asserted-by":"crossref","unstructured":"F. Barthe. \u201cLevels of concentration between exponential and Gaussian\u201d. In: Ann. Fac. Sci. Toulouse Math. (6) 10.3 (2001), pp.\u00a0393\u2013404.","DOI":"10.5802\/afst.997"},{"key":"9667_CR5","doi-asserted-by":"crossref","unstructured":"F. Barthe, P. Cattiaux, and C. Roberto. \u201cInterpolated inequalities between exponential and Gaussian, Orlicz hypercontractivity and isoperimetry\u201d. In: Rev. Mat. Iberoam. 22.3 (2006), pp.\u00a0993\u20131067.","DOI":"10.4171\/rmi\/482"},{"key":"9667_CR6","doi-asserted-by":"crossref","unstructured":"F. Barthe, P. Cattiaux, and C. Roberto. \u201cIsoperimetry between exponential and Gaussian\u201d. In: Electron. J. Probab. 12 (2007), no. 44, 1212\u20131237.","DOI":"10.1214\/EJP.v12-441"},{"key":"9667_CR7","doi-asserted-by":"crossref","unstructured":"F. Barthe and C. Roberto. \u201cSobolev inequalities for probability measures on the real line\u201d. In: vol.\u00a0159. 3. Dedicated to Professor Aleksander Pe łczy\u0144ski on the occasion of his 70th birthday (Polish). (2003), pp.\u00a0481\u2013497.","DOI":"10.4064\/sm159-3-9"},{"key":"9667_CR8","doi-asserted-by":"crossref","unstructured":"L. Bertini and B. Zegarlinski. \u201cCoercive inequalities for Gibbs measures\u201d. In: Journal of Functional Analysis 162.2 (1999), pp.\u00a0257\u2013286.","DOI":"10.1006\/jfan.1997.3157"},{"key":"9667_CR9","doi-asserted-by":"crossref","unstructured":"S.\u00a0G. Bobkov. \u201cIsoperimetric and analytic inequalities for log-concave probability measures\u201d. In: Ann. Probab. 27.4 (1999), pp.\u00a01903\u20131921.","DOI":"10.1214\/aop\/1022677553"},{"key":"9667_CR10","doi-asserted-by":"crossref","unstructured":"S.\u00a0G. Bobkov. \u201cSpectral gap and concentration for some spherically symmetric probability measures\u201d. In: Geometric aspects of functional analysis. Vol.\u00a01807. Lecture Notes in Math. Springer, Berlin, (2003), pp.\u00a037\u201343.","DOI":"10.1007\/978-3-540-36428-3_4"},{"key":"9667_CR11","doi-asserted-by":"crossref","unstructured":"F. Bolley and C. Villani. \u201cWeighted Csisz\u00e1r\u2013Kullback\u2013Pinsker inequalities and applications to transportation inequalities\u201d. In: Ann. Fac. Sci. Toulouse Math. (6) 14.3 (2005), pp.\u00a0331\u2013352.","DOI":"10.5802\/afst.1095"},{"key":"9667_CR12","doi-asserted-by":"crossref","unstructured":"S. Boucheron, O. Bousquet, G. Lugosi, and P. Massart. \u201cMoment inequalities for functions of independent random variables\u201d. In: Ann. Probab. 33.2 (2005), pp.\u00a0514\u2013560.","DOI":"10.1214\/009117904000000856"},{"key":"9667_CR13","doi-asserted-by":"crossref","unstructured":"S. Boucheron, G. Lugosi, and P. Massart. Concentration inequalities. A nonasymptotic theory of independence, With a foreword by Michel Ledoux. Oxford University Press, Oxford, (2013), pp.\u00a0x+481.","DOI":"10.1093\/acprof:oso\/9780199535255.001.0001"},{"key":"9667_CR14","doi-asserted-by":"crossref","unstructured":"S. Brooks, A. Gelman, G. Jones, and X.-L. Meng. Handbook of Markov chain Monte Carlo. CRC Press, 2011.","DOI":"10.1201\/b10905"},{"key":"9667_CR15","doi-asserted-by":"crossref","unstructured":"Y. Cao, J. Lu, and Y. Lu. \u201cExponential decay of R\u00e9nyi divergence under Fokker\u2013Planck equations\u201d. In: J. Stat. Phys. 176.5 (2019), pp.\u00a01172\u20131184.","DOI":"10.1007\/s10955-019-02339-8"},{"key":"9667_CR16","doi-asserted-by":"crossref","unstructured":"Y. Cao, J. Lu, and L. Wang. \u201cComplexity of randomized algorithms for underdamped Langevin dynamics\u201d. In: Commun. Math. Sci. 19.7 (2021), pp.\u00a01827\u20131853.","DOI":"10.4310\/CMS.2021.v19.n7.a4"},{"key":"9667_CR17","doi-asserted-by":"crossref","unstructured":"Y. Cao, J. Lu, and L. Wang. \u201cOn explicit $$L^2$$-convergence rate estimate for underdamped Langevin dynamics\u201d. In: Arch. Ration. Mech. Anal. 247.5 (2023), p.\u00a090.","DOI":"10.1007\/s00205-023-01922-4"},{"key":"9667_CR18","doi-asserted-by":"crossref","unstructured":"P. Cattiaux, I. Gentil, and A. Guillin. \u201cWeak logarithmic Sobolev inequalities and entropic convergence\u201d. In: Probab. Theory Related Fields 139.3-4 (2007), pp.\u00a0563\u2013603.","DOI":"10.1007\/s00440-007-0054-5"},{"key":"9667_CR19","doi-asserted-by":"crossref","unstructured":"D. Chafai. \u201cEntropies, convexity, and functional inequalities: on $$\\Phi $$-entropies and $$\\Phi $$-Sobolev inequalities\u201d. In: J. Math. Kyoto Univ. 44.2 (2004), pp.\u00a0325\u2013363.","DOI":"10.1215\/kjm\/1250283556"},{"key":"9667_CR20","unstructured":"N. Chatterji, J. Diakonikolas, M.\u00a0I. Jordan, and P. Bartlett. \u201cLangevin Monte Carlo without smoothness\u201d. In: Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics. Ed. by S. Chiappa and R. Calandra. Vol.\u00a0108. Proceedings of Machine Learning Research. PMLR, 2020, pp.\u00a01716\u20131726."},{"key":"9667_CR21","doi-asserted-by":"crossref","unstructured":"H.-B. Chen, S. Chewi, and J. Niles-Weed. \u201cDimension-free log-Sobolev inequalities for mixture distributions\u201d. In: Journal of Functional Analysis 281.11 (2021), p.\u00a0109236.","DOI":"10.1016\/j.jfa.2021.109236"},{"key":"9667_CR22","doi-asserted-by":"crossref","unstructured":"Y. Chen. \u201cAn almost constant lower bound of the isoperimetric coefficient in the KLS conjecture\u201d. In: Geom. Funct. Anal. 31.1 (2021), pp.\u00a034\u201361.","DOI":"10.1007\/s00039-021-00558-4"},{"key":"9667_CR23","unstructured":"Y. Chen, R. Dwivedi, M.\u00a0J. Wainwright, and B. Yu. \u201cFast MCMC sampling algorithms on polytopes\u201d. In: The Journal of Machine Learning Research 19.1 (2018), pp.\u00a02146\u20132231."},{"key":"9667_CR24","unstructured":"Y. Chen, R. Dwivedi, M.\u00a0J. Wainwright, and B. Yu. \u201cFast mixing of Metropolized Hamiltonian Monte Carlo: benefits of multi-step gradients\u201d. In: J. Mach. Learn. Res. 21 (2020), Paper No. 92, 71."},{"key":"9667_CR25","unstructured":"X. Cheng and P. Bartlett. \u201cConvergence of Langevin MCMC in KL-divergence\u201d. In: Algorithmic Learning Theory. PMLR. 2018, pp.\u00a0186\u2013211."},{"key":"9667_CR26","unstructured":"S. Chewi, P.\u00a0R. Gerber, C. Lu, T.\u00a0L. Gouic, and P. Rigollet. \u201cThe query complexity of sampling from strongly log-concave distributions in one dimension\u201d. In: Proceedings of Thirty Fifth Conference on Learning Theory. Ed. by P.-L. Loh and M. Raginsky. Vol.\u00a0178. Proceedings of Machine Learning Research. PMLR, July 2022, pp.\u00a02041\u20132059."},{"key":"9667_CR27","unstructured":"S. Chewi, T. Le Gouic, C. Lu, T. Maunu, P. Rigollet, and A.\u00a0J. Stromme. \u201cExponential ergodicity of mirror-Langevin diffusions\u201d. In: Advances in Neural Information Processing Systems. Ed. by H. Larochelle, M. Ranzato, R. Hadsell, M.\u00a0F. Balcan, and H. Lin. Vol.\u00a033. Curran Associates, Inc., 2020, pp.\u00a019573\u201319585."},{"key":"9667_CR28","unstructured":"S. Chewi, C. Lu, K. Ahn, X. Cheng, T.\u00a0L. Gouic, and P. Rigollet. \u201cOptimal dimension dependence of the Metropolis-adjusted Langevin algorithm\u201d. In: Proceedings of Thirty Fourth Conference on Learning Theory. Ed. by M. Belkin and S. Kpotufe. Vol.\u00a0134. Proceedings of Machine Learning Research. PMLR, 2021, pp.\u00a01260\u20131300."},{"key":"9667_CR29","unstructured":"S. Chewi, C. Lu, K. Ahn, X. Cheng, T. Le Gouic, and P. Rigollet. \u201cOptimal dimension dependence of the Metropolis-adjusted Langevin algorithm\u201d. In: Conference on Learning Theory. PMLR. 2021, pp.\u00a01260\u20131300."},{"key":"9667_CR30","unstructured":"A.\u00a0S. Dalalyan. \u201cFurther and stronger analogy between sampling and optimization: Langevin Monte Carlo and gradient descent\u201d. In: Proceedings of the 2017 Conference on Learning Theory. Ed. by S. Kale and O. Shamir. Vol.\u00a065. Proceedings of Machine Learning Research. PMLR, 2017, pp.\u00a0678\u2013689."},{"key":"9667_CR31","unstructured":"A.\u00a0S. Dalalyan, A. Karagulyan, and L. Riou-Durand. \u201cBounding the error of discretized Langevin algorithms for non-strongly log-concave targets\u201d. In: J. Mach. Learn. Res. 23 (2022), Paper No. 235, 38."},{"key":"9667_CR32","doi-asserted-by":"crossref","unstructured":"A.\u00a0S. Dalalyan and A.\u00a0B. Tsybakov. \u201cSparse regression learning by aggregation and Langevin Monte-Carlo\u201d. In: J. Comput. System Sci. 78.5 (2012), pp.\u00a01423\u20131443.","DOI":"10.1016\/j.jcss.2011.12.023"},{"key":"9667_CR33","doi-asserted-by":"crossref","unstructured":"O. Devolder, F. Glineur, and Y. Nesterov. \u201cFirst-order methods of smooth convex optimization with inexact oracle\u201d. In: Mathematical Programming 146.1 (2014), pp.\u00a037\u201375.","DOI":"10.1007\/s10107-013-0677-5"},{"key":"9667_CR34","unstructured":"A. Durmus, S. Majewski, and B. Miasojedow. \u201cAnalysis of Langevin Monte Carlo via convex optimization\u201d. In: J. Mach. Learn. Res. 20 (2019), Paper No. 73, 46."},{"key":"9667_CR35","unstructured":"R. Dwivedi, Y. Chen, M.\u00a0J. Wainwright, and B. Yu. \u201cLog-concave sampling: Metropolis\u2013Hastings algorithms are fast\u201d. In: Journal of Machine Learning Research 20.183 (2019), pp.\u00a01\u201342."},{"key":"9667_CR36","unstructured":"M. Erdogdu and R. Hosseinzadeh. \u201cOn the convergence of Langevin Monte Carlo: the interplay between tail growth and smoothness\u201d. In: Proceedings of Thirty Fourth Conference on Learning Theory. Ed. by M. Belkin and S. Kpotufe. Vol.\u00a0134. Proceedings of Machine Learning Research. PMLR, 2021, pp.\u00a01776\u20131822."},{"key":"9667_CR37","unstructured":"M.\u00a0A. Erdogdu, R. Hosseinzadeh, and S. Zhang. \u201cConvergence of Langevin Monte Carlo in chi-squared and R\u00e9nyi divergence\u201d. In: Proceedings of the 25th International Conference on Artificial Intelligence and Statistics. Ed. by G. Camps-Valls, F.\u00a0J.\u00a0R. Ruiz, and I. Valera. Vol.\u00a0151. Proceedings of Machine Learning Research. PMLR, 2022, pp.\u00a08151\u20138175."},{"key":"9667_CR38","unstructured":"M.\u00a0A. Erdogdu, L. Mackey, and O. Shamir. \u201cGlobal non-convex optimization with discretized diffusions\u201d. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2018, pp.\u00a09694\u20139703."},{"key":"9667_CR39","unstructured":"A. Ganesh and K. Talwar. \u201cFaster differentially private samplers via R\u00e9nyi divergence analysis of discretized Langevin MCMC\u201d. In: Advances in Neural Information Processing Systems. Ed. by H. Larochelle, M. Ranzato, R. Hadsell, M.\u00a0F. Balcan, and H. Lin. Vol.\u00a033. Curran Associates, Inc., 2020, pp.\u00a07222\u20137233."},{"key":"9667_CR40","doi-asserted-by":"crossref","unstructured":"A. Gelman, J.\u00a0B. Carlin, H.\u00a0S. Stern, D.\u00a0B. Dunson, A. Vehtari, and D.\u00a0B. Rubin. \u201cBayesian data analysis\u201d. In: Chapman Hall, London (2013).","DOI":"10.1201\/b16018"},{"key":"9667_CR41","doi-asserted-by":"crossref","unstructured":"J. Gorham, A.\u00a0B. Duncan, S.\u00a0J. Vollmer, and L. Mackey. \u201cMeasuring sample quality with diffusions\u201d. In: The Annals of Applied Probability 29.5 (2019), pp.\u00a02884\u20132928.","DOI":"10.1214\/19-AAP1467"},{"key":"9667_CR42","doi-asserted-by":"crossref","unstructured":"N. Gozlan. \u201cPoincar\u00e9 inequalities and dimension free concentration of measure\u201d. In: Annales de l\u2019IHP Probabilit \u00e9 s et statistiques. Vol.\u00a046. 3. (2010), pp.\u00a0708\u2013739.","DOI":"10.1214\/09-AIHP209"},{"key":"9667_CR43","doi-asserted-by":"crossref","unstructured":"L. Gross. \u201cLogarithmic Sobolev inequalities\u201d. In: American Journal of Mathematics 97.4 (1975), pp.\u00a01061\u20131083.","DOI":"10.2307\/2373688"},{"key":"9667_CR44","unstructured":"Y. He, K. Balasubramanian, and M.\u00a0A. Erdogdu. \u201cOn the ergodicity, bias and asymptotic normality of randomized midpoint sampling method\u201d. In: Advances in Neural Information Processing Systems. Ed. by H. Larochelle, M. Ranzato, R. Hadsell, M.\u00a0F. Balcan, and H. Lin. Vol.\u00a033. Curran Associates, Inc., 2020, pp.\u00a07366\u20137376."},{"key":"9667_CR45","doi-asserted-by":"crossref","unstructured":"D.\u00a0J. Higham, X. Mao, and A.\u00a0M. Stuart. \u201cStrong convergence of Euler-type methods for nonlinear stochastic differential equations\u201d. In: SIAM Journal on Numerical Analysis 40.3 (2002), pp.\u00a01041\u20131063.","DOI":"10.1137\/S0036142901389530"},{"key":"9667_CR46","doi-asserted-by":"crossref","unstructured":"R. Kannan, L. Lov\u00e1sz, and M. Simonovits. \u201cIsoperimetric problems for convex bodies and a localization lemma\u201d. In: Discrete Comput. Geom. 13.3-4 (1995), pp.\u00a0541\u2013559.","DOI":"10.1007\/BF02574061"},{"key":"9667_CR47","doi-asserted-by":"crossref","unstructured":"B. Klartag and J. Lehec. \u201cBourgain\u2019s slicing problem and KLS isoperimetry up to polylog\u201d. In: Geometric and Functional Analysis 32.5 (2022), pp.\u00a01134\u20131159.","DOI":"10.1007\/s00039-022-00612-9"},{"key":"9667_CR48","doi-asserted-by":"crossref","unstructured":"P.\u00a0E. Kloeden, E. Platen, P.\u00a0E. Kloeden, and E. Platen. Stochastic differential equations. Springer, 1992.","DOI":"10.1007\/978-3-662-12616-5"},{"key":"9667_CR49","doi-asserted-by":"crossref","unstructured":"R. Lata\u0142a and K. Oleszkiewicz. \u201cBetween Sobolev and Poincar\u00e9\u201d. In: Geometric aspects of functional analysis. Vol.\u00a01745. Lecture Notes in Math. Springer, Berlin, 2000, pp.\u00a0147\u2013168.","DOI":"10.1007\/BFb0107213"},{"key":"9667_CR50","unstructured":"Y.\u00a0T. Lee, R. Shen, and K. Tian. \u201cLogsmooth gradient concentration and tighter runtimes for Metropolized Hamiltonian Monte Carlo\u201d. In: Proceedings of Thirty Third Conference on Learning Theory. Ed. by J. Abernethy and S. Agarwal. Vol.\u00a0125. Proceedings of Machine Learning Research. PMLR, 2020, pp.\u00a02565\u20132597."},{"key":"9667_CR51","doi-asserted-by":"crossref","unstructured":"J. Lehec. \u201cThe Langevin Monte Carlo algorithm in the non-smooth log-concave case\u201d. In: Ann. Appl. Probab. 33.6A (2023), pp.\u00a04858\u20134874.","DOI":"10.1214\/23-AAP1935"},{"key":"9667_CR52","doi-asserted-by":"crossref","unstructured":"M.\u00a0B. Li and M.\u00a0A. Erdogdu. \u201cRiemannian Langevin algorithm for solving semidefinite programs\u201d. In: Bernoulli 29.4 (2023), pp.\u00a03093\u20133113.","DOI":"10.3150\/22-BEJ1576"},{"key":"9667_CR53","doi-asserted-by":"crossref","unstructured":"J. Liang and Y. Chen. \u201cA proximal algorithm for sampling from non-smooth potentials\u201d. In: arXiv e-prints, arXiv:2110.04597 (2021).","DOI":"10.1109\/WSC57314.2022.10015293"},{"key":"9667_CR54","doi-asserted-by":"crossref","unstructured":"Y. Liu. \u201cThe Poincar\u00e9 inequality and quadratic transportation-variance inequalities\u201d. In: Electron. J. Probab. 25 (2020), Paper No. 1, 16.","DOI":"10.1214\/19-EJP403"},{"key":"9667_CR55","doi-asserted-by":"crossref","unstructured":"L. Lov\u00e1sz and M. Simonovits. \u201cRandom walks in a convex body and an improved volume algorithm\u201d. In: Random Structures & Algorithms 4.4 (1993), pp.\u00a0359\u2013412.","DOI":"10.1002\/rsa.3240040402"},{"key":"9667_CR56","doi-asserted-by":"crossref","unstructured":"J. Lu and L. Wang. \u201cComplexity of zigzag sampling algorithm for strongly log-concave distributions\u201d. In: Stat. Comput. 32.3 (2022), Paper No. 48.","DOI":"10.1007\/s11222-022-10109-y"},{"key":"9667_CR57","unstructured":"D.\u00a0J. MacKay. Information theory, inference and learning algorithms. Cambridge University Press, (2003)."},{"key":"9667_CR58","unstructured":"P.\u00a0A. Markowich and C. Villani. \u201cOn the trend to equilibrium for the Fokker\u2013Planck equation: an interplay between physics and functional analysis\u201d. In: Mat. Contemp 19 (2000), pp.\u00a01\u201329."},{"key":"9667_CR59","doi-asserted-by":"crossref","unstructured":"J.\u00a0C. Mattingly, A.\u00a0M. Stuart, and D.\u00a0J. Higham. \u201cErgodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise\u201d. In: Stochastic Processes and Their Applications 101.2 (2002), pp.\u00a0185\u2013232.","DOI":"10.1016\/S0304-4149(02)00150-3"},{"key":"9667_CR60","unstructured":"L. Miclo. \u201cRecuit simul\u00e9 sur $${\\varvec {R}}^n$$. \u00c9tude de l\u2019\u00e9volution de l\u2019\u00e9nergie libre\u201d. In: Ann. Inst. H. Poincar \u00e9 Probab. Statist. 28.2 (1992), pp.\u00a0235\u2013266."},{"key":"9667_CR61","doi-asserted-by":"crossref","unstructured":"L. Miclo. Remarques sur l\u2019hypercontractivite et l\u2019evolution de l\u2019entropie pour des chaines de Markov finies. Springer, (1997).","DOI":"10.1007\/BFb0119300"},{"key":"9667_CR62","doi-asserted-by":"crossref","unstructured":"L. Miclo. \u201cUne majoration sous-exponentielle pour la convergence de l\u2019entropie des chaines de Markov a trou spectral\u201d. In: Ann. Inst. H. Poincare Probab. Statist. 35.3 (1999), pp.\u00a0261\u2013311.","DOI":"10.1016\/S0246-0203(99)80013-2"},{"key":"9667_CR63","doi-asserted-by":"crossref","unstructured":"G.\u00a0N. Milstein and M.\u00a0V. Tretyakov. Stochastic numerics for mathematical physics. Vol.\u00a039. Springer, (2004).","DOI":"10.1007\/978-3-662-10063-9"},{"key":"9667_CR64","doi-asserted-by":"crossref","unstructured":"G.\u00a0N. Milstein. Numerical integration of stochastic differential equations. Vol.\u00a0313. Springer Science & Business Media, (1994).","DOI":"10.1007\/978-94-015-8455-5"},{"key":"9667_CR65","doi-asserted-by":"crossref","unstructured":"W. Mou, N. Flammarion, M.\u00a0J. Wainwright, and P.\u00a0L. Bartlett. \u201cImproved bounds for discretization of Langevin diffusions: near-optimal rates without convexity\u201d. In: Bernoulli 28.3 (2022), pp.\u00a01577\u20131601.","DOI":"10.3150\/21-BEJ1343"},{"key":"9667_CR66","doi-asserted-by":"crossref","unstructured":"Y. Nesterov. \u201cUniversal gradient methods for convex optimization problems\u201d. In: Mathematical Programming 152.1 (2015), pp.\u00a0381\u2013404.","DOI":"10.1007\/s10107-014-0790-0"},{"key":"9667_CR67","doi-asserted-by":"crossref","unstructured":"D. Nguyen. \u201cUnadjusted Langevin algorithm for sampling a mixture of weakly smooth potentials\u201d. In: Braz. J. Probab. Stat. 36.3 (2022), pp.\u00a0504\u2013539.","DOI":"10.1214\/22-BJPS538"},{"key":"9667_CR68","doi-asserted-by":"crossref","unstructured":"D. Nguyen, X. Dang, and Y. Chen. \u201cUnadjusted Langevin algorithm for non-convex weakly smooth potentials\u201d. In: Communications in Mathematics and Statistics (2023).","DOI":"10.1007\/s40304-023-00350-w"},{"key":"9667_CR69","unstructured":"B. Oksendal. Stochastic differential equations: an introduction with applications. Springer Science & Business Media, (2013)."},{"key":"9667_CR70","doi-asserted-by":"crossref","unstructured":"G.\u00a0A. Pavliotis. Stochastic processes and applications: diffusion processes, the Fokker-Planck and Langevin equations. Vol.\u00a060. Springer, 2014.","DOI":"10.1007\/978-1-4939-1323-7"},{"key":"9667_CR71","unstructured":"M. Raginsky, A. Rakhlin, and M. Telgarsky. \u201cNon-convex learning via stochastic gradient Langevin dynamics: a nonasymptotic analysis\u201d. In: Proceedings of the 2017 Conference on Learning Theory. Ed. by S. Kale and O. Shamir. Vol.\u00a065. Proceedings of Machine Learning Research. PMLR, 2017, pp.\u00a01674\u20131703."},{"key":"9667_CR72","doi-asserted-by":"crossref","unstructured":"C.\u00a0P. Robert and G. Casella. Monte Carlo statistical methods. Second. Springer Texts in Statistics. Springer-Verlag, New York, 2004, pp.\u00a0xxx+645.","DOI":"10.1007\/978-1-4757-4145-2"},{"key":"9667_CR73","unstructured":"R. Shen and Y.\u00a0T. Lee. \u201cThe randomized midpoint method for log-concave sampling\u201d. In: Advances in Neural Information Processing Systems. Ed. by H. Wallach, H. Larochelle, A. Beygelzimer, F. d\u2019Alch\u00e9-Buc, E. Fox, and R. Garnett. Vol.\u00a032. Curran Associates, Inc., 2019."},{"key":"9667_CR74","doi-asserted-by":"crossref","unstructured":"G. Toscani and C. Villani. \u201cOn the trend to equilibrium for some dissipative systems with slowly increasing a priori bounds\u201d. In: Journal of Statistical Physics 98.5 (2000), pp.\u00a01279\u20131309.","DOI":"10.1023\/A:1018623930325"},{"key":"9667_CR75","unstructured":"S. Vempala and A. Wibisono. \u201cRapid convergence of the unadjusted Langevin algorithm: isoperimetry suffices\u201d. In: Advances in Neural Information Processing Systems. Ed. by H. Wallach, H. Larochelle, A. Beygelzimer, F. d\u2019Alch\u00e9-Buc, E. Fox, and R. Garnett. Vol.\u00a032. Curran Associates, Inc., 2019."},{"key":"9667_CR76","doi-asserted-by":"crossref","unstructured":"R. Vershynin. High-dimensional probability. Vol.\u00a047. Cambridge Series in Statistical and Probabilistic Mathematics. An introduction with applications in data science, With a foreword by Sara van de Geer. Cambridge University Press, Cambridge, 2018, pp.\u00a0xiv+284.","DOI":"10.1017\/9781108231596"},{"key":"9667_CR77","doi-asserted-by":"crossref","unstructured":"F.-Y. Wang. \u201cFunctional inequalities for empty essential spectrum\u201d. In: J. Funct. Anal. 170.1 (2000), pp.\u00a0219\u2013245.","DOI":"10.1006\/jfan.1999.3516"},{"key":"9667_CR78","doi-asserted-by":"crossref","unstructured":"F.-Y. Wang. \u201cA generalization of Poincar\u00e9 and log-Sobolev inequalities\u201d. In: Potential Anal. 22.1 (2005), pp.\u00a01\u201315.","DOI":"10.1007\/s11118-003-4006-0"},{"key":"9667_CR79","unstructured":"A. Wibisono. \u201cProximal Langevin algorithm: rapid convergence under isoperimetry\u201d. In: arXiv e-prints, arXiv:1911.01469 (2019)."},{"key":"9667_CR80","unstructured":"K. Wu, S. Schmidler, and Y. Chen. \u201cMinimax mixing time of the Metropolis-adjusted Langevin algorithm for log-concave sampling\u201d. In: Journal of Machine Learning Research 23.270 (2022), pp.\u00a01\u201363."},{"key":"9667_CR81","doi-asserted-by":"crossref","unstructured":"B. Zegarlinski. \u201cEntropy bounds for Gibbs measures with non-Gaussian tails\u201d. In: Journal of Functional Analysis 187.2 (2001), pp.\u00a0368\u2013395.","DOI":"10.1006\/jfan.2001.3808"}],"container-title":["Foundations of Computational Mathematics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10208-024-09667-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10208-024-09667-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10208-024-09667-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T17:21:33Z","timestamp":1756401693000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10208-024-09667-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,26]]},"references-count":81,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["9667"],"URL":"https:\/\/doi.org\/10.1007\/s10208-024-09667-6","relation":{},"ISSN":["1615-3375","1615-3383"],"issn-type":[{"value":"1615-3375","type":"print"},{"value":"1615-3383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,26]]},"assertion":[{"value":"19 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}