Automatic structured variational inference

被引:0
作者
Ambrogioni, Luca [1 ]
Lin, Kate [2 ]
Fertig, Emily [2 ]
Vikram, Sharad [2 ]
Hinne, Max [1 ]
Moore, Dave [2 ]
van Gerven, Marcel [1 ]
机构
[1] Radboud Univ Nijmegen, Donders Inst Brain Cognit & Behav, Dept Artificial Intelligence, Nijmegen, Netherlands
[2] Google Res, San Francisco, CA USA
来源
24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS) | 2021年 / 130卷
关键词
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
Stochastic variational inference offers an attractive option as a default method for differentiable probabilistic programming. However, the performance of the variational approach depends on the choice of an appropriate variational family. Here, we introduce automatic structured variational inference (ASVI), a fully automated method for constructing structured variational families, inspired by the closed-form update in conjugate Bayesian models. These convex-update families incorporate the forward pass of the input probabilistic program and can therefore capture complex statistical dependencies. Convex-update families have the same space and time complexity as the input probabilistic program and are therefore tractable for a very large family of models including both continuous and discrete variables. We validate our automatic variational method on a wide range of low- and high-dimensional inference problems. We find that ASVI provides a clear improvement in performance when compared with other popular approaches such as the mean-field approach and inverse autoregressive flows. We provide an open source implementation of ASVI in TensorFlow Probability.
引用
收藏
页码:676 / +
页数:10
相关论文
共 42 条
  • [1] [Anonymous], 2014, INT C MACH LEARN
  • [2] [Anonymous], 2018, ADV NEURAL INFORM PR
  • [3] [Anonymous], 2015, INT C MACH LEARN
  • [4] [Anonymous], 2014, TEXTS STAT SCI, DOI DOI 10.1201/B16018
  • [5] Bingham E, 2019, J MACH LEARN RES, V20
  • [6] Stan: A Probabilistic Programming Language
    Carpenter, Bob
    Gelman, Andrew
    Hoffman, Matthew D.
    Lee, Daniel
    Goodrich, Ben
    Betancourt, Michael
    Brubaker, Marcus A.
    Guo, Jiqiang
    Li, Peter
    Riddell, Allen
    [J]. JOURNAL OF STATISTICAL SOFTWARE, 2017, 76 (01): : 1 - 29
  • [7] Chen T. Q., 2018, ADV NEURAL INFORM PR
  • [8] Clanuwat T., 2018, ARXIV PREPRINT ARXIV
  • [9] CONJUGATE PRIORS FOR EXPONENTIAL FAMILIES
    DIACONIS, P
    YLVISAKER, D
    [J]. ANNALS OF STATISTICS, 1979, 7 (02) : 269 - 281
  • [10] Dillon J. V., 2020, ARXIV PREPRINT ARXIV