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] 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
  • [42] 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,
  • [43] 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
  • [44] 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
  • [45] Hybrid Monte Carlo without pseudofermions
    Liu, KF
    Dong, SJ
    Thron, C
    NUCLEAR PHYSICS B, 1997, : 980 - 982
  • [46] Sequential Monte Carlo without likelihoods
    Sisson, S. A.
    Fan, Y.
    Tanaka, Mark M.
    PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2007, 104 (06) : 1760 - 1765
  • [47] Sampling from a Log-Concave Distribution with Projected Langevin Monte Carlo
    Bubeck, Sebastien
    Eldan, Ronen
    Lehec, Joseph
    DISCRETE & COMPUTATIONAL GEOMETRY, 2018, 59 (04) : 757 - 783
  • [48] Bregman Proximal Langevin Monte Carlo via Bregman-Moreau Envelopes
    Lau, Tim Tsz-Kit
    Liu, Han
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [49] LANGEVIN-BASED STRATEGY FOR EFFICIENT PROPOSAL ADAPTATION IN POPULATION MONTE CARLO
    Elvira, Victor
    Chouzenoux, Emilie
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 5077 - 5081
  • [50] Improving multilevel Monte Carlo for stochastic differential equations with application to the Langevin equation
    Mueller, Eike H.
    Scheichl, Rob
    Shardlow, Tony
    PROCEEDINGS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, 2015, 471 (2176):