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
  • [1] Likelihood-free approximate Gibbs sampling
    Rodrigues, G. S.
    Nott, David J.
    Sisson, S. A.
    STATISTICS AND COMPUTING, 2020, 30 (04) : 1057 - 1073
  • [2] Likelihood-Free Parameter Estimation with Neural Bayes Estimators
    Sainsbury-Dale, Matthew
    Zammit-Mangion, Andrew
    Huser, Raphael
    AMERICAN STATISTICIAN, 2024, 78 (01) : 1 - 14
  • [3] Likelihood-free parallel tempering
    Baragatti, Meili
    Grimaud, Agnes
    Pommeret, Denys
    STATISTICS AND COMPUTING, 2013, 23 (04) : 535 - 549
  • [4] Efficient likelihood-free Bayesian Computation for household epidemics
    Neal, Peter
    STATISTICS AND COMPUTING, 2012, 22 (06) : 1239 - 1256
  • [5] Likelihood-free inference via classification
    Gutmann, Michael U.
    Dutta, Ritabrata
    Kaski, Samuel
    Corander, Jukka
    STATISTICS AND COMPUTING, 2018, 28 (02) : 411 - 425
  • [6] Expectation Propagation for Likelihood-Free Inference
    Barthelme, Simon
    Chopin, Nicolas
    JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2014, 109 (505) : 315 - 333
  • [7] Likelihood-free estimation of model evidence
    Didelot, Xavier
    Everitt, Richard G.
    Johansen, Adam M.
    Lawson, Daniel J.
    BAYESIAN ANALYSIS, 2011, 6 (01): : 49 - 76
  • [8] Maximum Likelihood Estimators on MCMC Sampling Algorithms for Decision Making
    Karras, Christos
    Karras, Aristeidis
    Avlonitis, Markos
    Giannoukou, Ioanna
    Sioutas, Spyros
    ARTIFICIAL INTELLIGENCE APPLICATIONS AND INNOVATIONS. AIAI 2022 IFIP WG 12.5 INTERNATIONAL WORKSHOPS, 2022, 652 : 345 - 356
  • [9] LIKELIHOOD-FREE COSMOLOGICAL INFERENCE WITH TYPE Ia SUPERNOVAE: APPROXIMATE BAYESIAN COMPUTATION FOR A COMPLETE TREATMENT OF UNCERTAINTY
    Weyant, Anja
    Schafer, Chad
    Wood-Vasey, W. Michael
    ASTROPHYSICAL JOURNAL, 2013, 764 (02)
  • [10] Reliable Gradient-free and Likelihood-free Prompt Tuning
    Shen, Maohao
    Ghosh, Soumya
    Sattigeri, Prasanna
    Das, Subhro
    Bu, Yuheng
    Wornell, Gregory
    17TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EACL 2023, 2023, : 2416 - 2429