Likelihood-free MCMC with Amortized Approximate Ratio Estimators

被引:0
作者
Hermans, Joeri [1 ]
Begy, Volodimir [2 ]
Louppe, Gilles [1 ]
机构
[1] Univ Liege, Liege, Belgium
[2] Univ Vienna, Vienna, Austria
来源
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 119 | 2020年 / 119卷
关键词
CHAIN MONTE-CARLO; BAYESIAN COMPUTATION; INFERENCE;
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
Posterior inference with an intractable likelihood is becoming an increasingly common task in scientific domains which rely on sophisticated computer simulations. Typically, these forward models do not admit tractable densities forcing practitioners to make use of approximations. This work introduces a novel approach to address the intractability of the likelihood and the marginal model. We achieve this by learning a flexible amortized estimator which approximates the likelihood-to-evidence ratio. We demonstrate that the learned ratio estimator can be embedded in MCMC samplers to approximate likelihood-ratios between consecutive states in the Markov chain, allowing us to draw samples from the intractable posterior. Techniques are presented to improve the numerical stability and to measure the quality of an approximation. The accuracy of our approach is demonstrated on a variety of benchmarks against well-established techniques. Scientific applications in physics show its applicability.
引用
收藏
页数:12
相关论文
共 32 条
  • [21] ABC likelihood-free methods for model choice in Gibbs random fields
    Grelaud, Aude
    Robert, Christian P.
    Marin, Jean-Michel
    Rodolphe, Francois
    Taly, Jean-Francois
    BAYESIAN ANALYSIS, 2009, 4 (02): : 317 - 335
  • [22] Likelihood-Free Inference of Population Structure and Local Adaptation in a Bayesian Hierarchical Model
    Bazin, Eric
    Dawson, Kevin J.
    Beaumont, Mark A.
    GENETICS, 2010, 185 (02) : 587 - 602
  • [23] Bayesian likelihood-free localisation of a biochemical source using multiple dispersion models
    Ristic, Branko
    Gunatilaka, Ajith
    Gailis, Ralph
    Skvortsov, Alex
    SIGNAL PROCESSING, 2015, 108 : 13 - 24
  • [24] Likelihood-free simulation-based optimal design with an application to spatial extremes
    Hainy, Markus
    Mueller, Werner G.
    Wagner, Helga
    STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT, 2016, 30 (02) : 481 - 492
  • [25] A Likelihood-Free Estimator of Population Structure Bridging Admixture Models and Principal Components Analysis
    Cabreros, Irineo
    Storey, John D.
    GENETICS, 2019, 212 (04) : 1009 - 1029
  • [26] Machine learning accelerated likelihood-free event reconstruction in dark matter direct detection
    Simola, U.
    Pelssers, B.
    Barge, D.
    Conrad, J.
    Corander, J.
    JOURNAL OF INSTRUMENTATION, 2019, 14 (03)
  • [27] Likelihood-free Cosmological Constraints with Artificial Neural Networks: An Application on Hubble Parameters and SNe Ia
    Wang, Yu-Chen
    Xie, Yuan-Bo
    Zhang, Tong-Jie
    Huang, Hui-Chao
    Zhang, Tingting
    Liu, Kun
    ASTROPHYSICAL JOURNAL SUPPLEMENT SERIES, 2021, 254 (02)
  • [28] A likelihood-free approach towards Bayesian modeling of degradation growths using mixed-effects regression
    Hazra, Indranil
    Pandey, Mahesh D.
    COMPUTERS & STRUCTURES, 2021, 244
  • [29] High-Dimensional Density Ratio Estimation with Extensions to Approximate Likelihood Computation
    Izbicki, Rafael
    Lee, Ann B.
    Schafer, Chad M.
    ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 33, 2014, 33 : 420 - 429
  • [30] Likelihood-free parameter estimation for dynamic queueing networks: Case study of passenger flow in an international airport terminal
    Ebert, Anthony
    Dutta, Ritabrata
    Mengersen, Kerrie
    Mira, Antonietta
    Ruggeri, Fabrizio
    Wu, Paul
    JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES C-APPLIED STATISTICS, 2021, 70 (03) : 770 - 792