Nonlinear MCMC for Bayesian Machine Learning

被引：0
|
作者：
Vuckovic, James
机构：
来源：
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022) | 2022年
关键词：
CHAIN MONTE-CARLO; MARKOV-PROCESSES; LANGEVIN; SIMULATION; ERGODICITY;
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：
We explore the application of a nonlinear MCMC technique first introduced in [1] to problems in Bayesian machine learning. We provide a convergence guarantee in total variation that uses novel results for long-time convergence and large-particle ("propagation of chaos") convergence. We apply this nonlinear MCMC technique to sampling problems including a Bayesian neural network on CIFAR10.
引用
收藏
页数：14
相关论文
共 50 条
  • [1] An Introduction to MCMC for Machine Learning
    Christophe Andrieu
    Nando de Freitas
    Arnaud Doucet
    Michael I. Jordan
    [J]. Machine Learning, 2003, 50 : 5 - 43
  • [2] An introduction to MCMC for machine learning
    Andrieu, C
    de Freitas, N
    Doucet, A
    Jordan, MI
    [J]. MACHINE LEARNING, 2003, 50 (1-2) : 5 - 43
  • [3] Bayesian MCMC nonlinear time series prediction
    Nakada, Y
    Kurihara, T
    Matsumoto, T
    [J]. 2001 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-VI, PROCEEDINGS: VOL I: SPEECH PROCESSING 1; VOL II: SPEECH PROCESSING 2 IND TECHNOL TRACK DESIGN & IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS NEURALNETWORKS FOR SIGNAL PROCESSING; VOL III: IMAGE & MULTIDIMENSIONAL SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING - VOL IV: SIGNAL PROCESSING FOR COMMUNICATIONS; VOL V: SIGNAL PROCESSING EDUCATION SENSOR ARRAY & MULTICHANNEL SIGNAL PROCESSING AUDIO & ELECTROACOUSTICS; VOL VI: SIGNAL PROCESSING THEORY & METHODS STUDENT FORUM, 2001, : 3509 - 3512
  • [4] Bayesian function learning using MCMC methods
    Magni, P
    Bellazzi, R
    De Nicolao, G
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1998, 20 (12) : 1319 - 1331
  • [5] The Neighborhood MCMC sampler for learning Bayesian networks
    Alyami, Salem A.
    Azad, A. K. M.
    Keith, Jonathan M.
    [J]. FIRST INTERNATIONAL WORKSHOP ON PATTERN RECOGNITION, 2016, 0011
  • [6] Bayesian model learning based on a parallel MCMC strategy
    Jukka Corander
    Mats Gyllenberg
    Timo Koski
    [J]. Statistics and Computing, 2006, 16 : 355 - 362
  • [7] Learning Dynamic Bayesian Networks using evolutionary MCMC
    Wang, Hao
    Yu, Kui
    Yao, Hongliang
    [J]. 2006 INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY, PTS 1 AND 2, PROCEEDINGS, 2006, : 45 - 50
  • [8] An EM-MCMC Algorithm for Bayesian Structure Learning
    Guo, Peng
    Li, Naixiang
    [J]. 2009 2ND IEEE INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND INFORMATION TECHNOLOGY, VOL 1, 2009, : 158 - 162
  • [9] Bayesian model learning based on a parallel MCMC strategy
    Corander, Jukka
    Gyllenberg, Mats
    Koski, Timo
    [J]. STATISTICS AND COMPUTING, 2006, 16 (04) : 355 - 362
  • [10] Layering-MCMC for Structure Learning in Bayesian Networks
    Viinikka, Jussi
    Koivisto, Mikko
    [J]. CONFERENCE ON UNCERTAINTY IN ARTIFICIAL INTELLIGENCE (UAI 2020), 2020, 124 : 839 - 848
12345