Langevin Monte Carlo without smoothness

被引:0
|
作者
Chatterji, Niladri S. [1 ]
Diakonikolas, Jelena [2 ]
Jordan, Michael I. [1 ]
Bartlett, Peter L. [1 ]
机构
[1] Univ Calif Berkeley, Berkeley, CA 94720 USA
[2] UW Madison, Madison, WI USA
关键词
ALGORITHM;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Langevin Monte Carlo (LMC) is an iterative algorithm used to generate samples from a distribution that is known only up to a normalizing constant. The nonasymptotic dependence of its mixing time on the dimension and target accuracy is understood mainly in the setting of smooth (gradient-Lipschitz) log-densities, a serious limitation for applications in machine learning. In this paper, we remove this limitation, providing polynomial-time convergence guarantees for a variant of LMC in the setting of nonsmooth log-concave distributions. At a high level, our results follow by leveraging the implicit smoothing of the log-density that comes from a small Gaussian perturbation that we add to the iterates of the algorithm and controlling the bias and variance that are induced by this perturbation.
引用
收藏
页码:1716 / 1725
页数:10
相关论文
共 50 条
  • [41] Convergence of Langevin Monte Carlo in Chi-Squared and Renyi Divergence
    Erdogdu, Murat A.
    Hosseinzadeh, Rasa
    Zhang, Matthew S.
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 151, 2022, 151
  • [42] NUMERICAL-INTEGRATION OF THE LANGEVIN EQUATION - MONTE-CARLO SIMULATION
    ERMAK, DL
    BUCKHOLZ, H
    JOURNAL OF COMPUTATIONAL PHYSICS, 1980, 35 (02) : 169 - 182
  • [43] Variance reduction for Random Coordinate Descent-Langevin Monte Carlo
    Ding, Zhiyan
    Li, Qin
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
  • [44] Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and Beyond
    Li, Xuechen
    Wu, Denny
    Mackey, Lester
    Erdogdu, Murat A.
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
  • [45] Analysis of Langevin Monte Carlo from Poincare to Log-Sobolev
    Chewi, Sinho
    Erdogdu, Murat A.
    Li, Mufan
    Shen, Ruoqi
    Zhang, Matthew
    CONFERENCE ON LEARNING THEORY, VOL 178, 2022, 178 : 1 - 2
  • [46] Comparison of hybrid Monte Carlo and Langevin dynamics for conformational sampling.
    Bernacki, K
    ABSTRACTS OF PAPERS OF THE AMERICAN CHEMICAL SOCIETY, 2001, 222 : U403 - U403
  • [47] 空间噪声和Langevin方程的Monte Carlo模拟
    周妍
    包景东
    清华大学学报(自然科学版), 2007, (S1) : 1027 - 1030
  • [48] Analysis of Langevin Monte Carlo from Poincaré to Log-Sobolev
    Chewi, Sinho
    Erdogdu, Murat A.
    Li, Mufan
    Shen, Ruoqi
    Zhang, Matthew S.
    FOUNDATIONS OF COMPUTATIONAL MATHEMATICS, 2024,
  • [49] Molecular dynamics, Langevin and hybrid Monte Carlo simulations in a multicanonical ensemble
    Hansmann, UHE
    Okamoto, Y
    Eisenmenger, F
    CHEMICAL PHYSICS LETTERS, 1996, 259 (3-4) : 321 - 330
  • [50] Towards a Complete Analysis of Langevin Monte Carlo: Beyond Poincare Inequality
    Mousavi-Hosseini, Alireza
    Farghly, Tyler
    He, Ye
    Balasubramanian, Krishnakumar
    Erdogdu, Murat A.
    THIRTY SIXTH ANNUAL CONFERENCE ON LEARNING THEORY, VOL 195, 2023, 195 : 1 - 35