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
下载
收藏
页码:1716 / 1725
页数:10
相关论文
共 50 条
  • [21] Finite-Time Analysis of Projected Langevin Monte Carlo
    Bubeck, Sebastien
    Eldan, Ronen
    Lehec, Joseph
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 28 (NIPS 2015), 2015, 28
  • [22] Decentralized Stochastic Gradient Langevin Dynamics and Hamiltonian Monte Carlo
    Gurbuzbalaban, Mert
    Gao, Xuefeng
    Hu, Yuanhan
    Zhu, Lingjiong
    JOURNAL OF MACHINE LEARNING RESEARCH, 2021, 22
  • [23] Convergence Rates for the Constrained Sampling via Langevin Monte Carlo
    Zhu, Yuanzheng
    ENTROPY, 2023, 25 (08)
  • [24] Decentralized stochastic gradient langevin dynamics and hamiltonian Monte Carlo
    Gürbüzbalaban, Mert
    Gao, Xuefeng
    Hu, Yuanhan
    Zhu, Lingjiong
    Journal of Machine Learning Research, 2021, 22
  • [25] Fractional Langevin Monte Carlo: Exploring Levy Driven Stochastic Differential Equations for Markov Chain Monte Carlo
    Simsekli, Umut
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 70, 2017, 70
  • [26] Metropolis Monte Carlo for tomographic reconstruction with prior smoothness information
    Barbuzza, R.
    Clausse, A.
    IET IMAGE PROCESSING, 2011, 5 (02) : 198 - 204
  • [27] Smoothness and dimension reduction in quasi-Monte Carlo methods
    Moskowitz, B
    Caflisch, RE
    MATHEMATICAL AND COMPUTER MODELLING, 1996, 23 (8-9) : 37 - 54
  • [28] Sparse regression learning by aggregation and Langevin Monte-Carlo
    Dalalyan, A. S.
    Tsybakov, A. B.
    JOURNAL OF COMPUTER AND SYSTEM SCIENCES, 2012, 78 (05) : 1423 - 1443
  • [29] Smoothness and Dimension Reduction in Quasi-Monte Carlo Methods
    Moskowitz, B.
    Caflisch, R. E.
    Mathematical and Computer Modelling (Oxford), 23 (8-9):
  • [30] Influence of Monte Carlo beamlet smoothness on plan metric accuracy
    Wattson, D.
    Cui, J.
    Wilkens, J.
    Deasy, J.
    MEDICAL PHYSICS, 2007, 34 (06) : 2462 - 2462