Help
Cart
Skip main navigation

Available Issues

April 10, 2013 - May 8, 2026

Available Issues

April 10, 2013 - May 8, 2026

Multilevel Langevin Pathwise Average for Gibbs Approximation

Published Online:20 Mar 2024https://doi.org/10.1287/moor.2021.0243

References

  • [1] Bou-Rabee N, Hairer M (2013) Nonasymptotic mixing of the MALA algorithm. IMA J. Numer. Anal. 33(1):80–110.Crossref, Google Scholar
  • [2] Chewi S, Lu C, Ahn K, Cheng X, Le Gouic T, Rigollet P (2021) Optimal dimension dependence of the Metropolis-adjusted Langevin algorithm. Belkin M, Kpotufe S, eds. Proc. 34th Conf. Learn. Theory. Proceedings of Machine Learning Research, vol. 134 (JMLR.org), 1260–1300.Google Scholar
  • [3] Dalalyan AS (2017) Theoretical guarantees for approximate sampling from smooth and log-concave densities. J. Royal Statist. Soc. Ser. B. 79(3):651–676.Crossref, Google Scholar
  • [4] Dalalyan AS, Karagulyan A (2019) User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient. Stochastic Processes Their Appl. 129(12):5278–5311.Crossref, Google Scholar
  • [5] Dalalyan AS, Grappin E, Paris Q (2018) On the exponentially weighted aggregate with the Laplace prior. Ann. Statist. 46(5):2452–2478.Crossref, Google Scholar
  • [6] Dalalyan AS, Karagulyan A, Riou-Durand L (2022) Bounding the error of discretized Langevin algorithms for non-strongly log-concave targets. J. Machine Learn. Res. 23(235):1–38.Google Scholar
  • [7] Durmus A, Moulines É (2015) Quantitative bounds of convergence for geometrically ergodic Markov chain in the Wasserstein distance with application to the Metropolis adjusted Langevin algorithm. Statist. Comput. 25(1):5–19.Crossref, Google Scholar
  • [8] Durmus A, Moulines É (2017) Nonasymptotic convergence analysis for the unadjusted Langevin algorithm. Ann. Appl. Probab. 27(3):1551–1587.Crossref, Google Scholar
  • [9] Durmus A, Moulines É (2019) High-dimensional Bayesian inference via the unadjusted Langevin algorithm. Bernoulli 25(4A):2854–2882.Crossref, Google Scholar
  • [10] Durmus A, Moulines É (2023) On geometric convergence for the Metropolis-adjusted Langevin algorithm under simple conditions. Biometrika 111(1):273–289.Google Scholar
  • [11] Durmus A, Majewski S, Miasojedow B (2019) Analysis of Langevin Monte Carlo via convex optimization. J. Machine Learn. Res. 20(1):2666–2711.Google Scholar
  • [12] Dwivedi R, Chen Y, Wainwright MJ, Yu B (2019) Log-concave sampling: Metropolis-Hastings algorithms are fast. J. Machine Learn. Res. 20(183):1–42.Google Scholar
  • [13] Fang W, Giles MB (2020) Adaptive Euler–Maruyama method for SDEs with nonglobally Lipschitz drift. Ann. Appl. Probab. 30(2):526–560.Crossref, Google Scholar
  • [14] Gadat S, Panloup F, Pellegrini C (2020) On the cost of Bayesian posterior mean strategy for log-concave models. Preprint, submitted October 8, https://arxiv.org/abs/2010.06420.Google Scholar
  • [15] Giles MB (2008) Multilevel Monte Carlo path simulation. Oper. Res. 56(3):607–617.Link, Google Scholar
  • [16] Giles MB, Majka MB, Szpruch L, Vollmer SJ, Zygalakis KC (2020) Multi-level Monte Carlo methods for the approximation of invariant measures of stochastic differential equations. Statist. Comput. 30(3):507–524.Crossref, Google Scholar
  • [17] Glynn PW, Rhee CH (2014) Exact estimation for Markov chain equilibrium expectations. J. Appl. Probab. 51A:377–389.Crossref, Google Scholar
  • [18] Heinrich S (2001) Multilevel Monte Carlo methods. Margenov S, Waśniewski J, Yalamov P, eds. Large-Scale Scientific Computing (Springer, Berlin), 58–67.Crossref, Google Scholar
  • [19] Karagulyan A, Dalalyan AS (2020) Penalized Langevin dynamics with vanishing penalty for smooth and log-concave targets. Preprint, submitted June 24, https://arxiv.org/abs/2006.13998.Google Scholar
  • [20] Kebaier A (2005) Statistical Romberg extrapolation: A new variance reduction method and applications to option pricing. Ann. Appl. Probab. 15(4):2681–2705.Crossref, Google Scholar
  • [21] Lamberton D, Pagès G (2002) Recursive computation of the invariant distribution of a diffusion. Bernoulli 8(3):367–405.Google Scholar
  • [22] Lamberton D, Pagès G (2003) Recursive computation of the invariant distribution of a diffusion: The case of a weakly mean reverting drift. Stochastics Dynam. 3(4):435–451.Crossref, Google Scholar
  • [23] Lemaire V (2007) An adaptive scheme for the approximation of dissipative systems. Stochastic Processes Their Appl. 117(10):1491–1518.Crossref, Google Scholar
  • [24] Lemaire V (2007) Behavior of the Euler scheme with decreasing step in a degenerate situation. ESAIM: Probab. Statist. 11:236–247.Crossref, Google Scholar
  • [25] Lemaire V, Pagès G, Panloup F (2015) Invariant measure of duplicated diffusions and application to Richardson-Romberg extrapolation. Ann. Inst. Henri Poincaré Probab. Statist. 51(4):1562–1596.Google Scholar
  • [26] Mattingly JC, Stuart AM, Higham DJ (2002) Ergodicity for SDEs and approximations: Locally Lipschitz vector fields and degenerate noise. Stochastic Processes Their Appl. 101(2):185–232.Crossref, Google Scholar
  • [27] McLeish D (2011) A general method for debiasing a Monte Carlo estimator. Monte Carlo Methods Appl. 17(4):301–315.Crossref, Google Scholar
  • [28] Metropolis N, Rosenbluth AW, Rosenbluth MN, Teller AH, Teller E (1953) Equation of state calculations by fast computing machines. J. Chemical Phys. 21(6):1087–1092.Crossref, Google Scholar
  • [29] Meyn SP, Tweedie RL (1993) Markov Chains and Stochastic Stability. Communications and Control Engineering Series (Springer-Verlag, London).Crossref, Google Scholar
  • [30] Mou W, Flammarion N, Wainwright MJ, Bartlett PL (2019) Improved bounds for discretization of Langevin diffusions: Near-optimal rates without convexity. Preprint, submitted July 25, https://arxiv.org/abs/1907.11331.Google Scholar
  • [31] Pagès G (2001) Sur quelques algorithmes récursifs pour les probabilités numériques. ESAIM Probab. Statist. 5:141–170.Crossref, Google Scholar
  • [32] Pagès G, Panloup F (2009) Approximation of the distribution of a stationary Markov process with application to option pricing. Bernoulli 15(1):146–177.Crossref, Google Scholar
  • [33] Pagès G, Panloup F (2014) A mixed-step algorithm for the approximation of the stationary regime of a diffusion. Stochastic Processes Their Appl. 124(1):522–565.Crossref, Google Scholar
  • [34] Pagès G, Panloup F (2018) Weighted multilevel Langevin simulation of invariant measures. Ann. Appl. Probab. 28(6):3358–3417.Crossref, Google Scholar
  • [35] Panloup F (2008) Recursive computation of the invariant measure of a stochastic differential equation driven by a Lévy process. Ann. Appl. Probab. 18(2):379–426.Crossref, Google Scholar
  • [36] Roberts GO, Tweedie RL (1996) Exponential convergence of Langevin distributions and their discrete approximations. Bernoulli 2(4):341–363.Crossref, Google Scholar
  • [37] Talay D (1990) Second order discretization schemes of stochastic differential systems for the computation of the invariant law. Stochastics Stochastic Rep. 29(1):13–36.Crossref, Google Scholar
  • [38] Vihola M (2018) Unbiased estimators and multilevel Monte Carlo. Oper. Res. 66(2):448–462.Link, Google Scholar
  • [39] Villani C (2009) Optimal Transport. Grundlehren der Mathematischen Wissenschaften [Fundamental Principles of Mathematical Sciences], vol. 338 (Springer, Berlin).Crossref, Google Scholar
Previous
Back to Top
Next
INFORMS site uses cookies to store information on your computer. Some are essential to make our site work; Others help us improve the user experience. By using this site, you consent to the placement of these cookies. Please read our Privacy Statement to learn more.
Agree