More Web Proxy on the site http://driver.im/

Article

Markov Chain Monte Carlo and variational inference: bridging the gap

Authors:

Diederik P. Kingma,

Max WellingAuthors Info & Claims

ICML'15: Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37

Pages 1218 - 1226

Published: 06 July 2015 Publication History

Abstract

Recent advances in stochastic gradient variational inference have made it possible to perform variational Bayesian inference with posterior approximations containing auxiliary random variables. This enables us to explore a new synthesis of variational inference and Monte Carlo methods where we incorporate one or more steps of MCMC into our variational approximation. By doing so we obtain a rich class of inference algorithms bridging the gap between variational methods and MCMC, and offering the best of both worlds: fast posterior approximation through the maximization of an explicit objective, with the option of trading off additional computation for additional accuracy. We describe the theoretical foundations that make this possible and show some promising first results.

References

[1]

Adler, Stephen L. Over-relaxation method for the monte carlo evaluation of the partition function for multiquadratic actions. Physical Review D, 23(12):2901, 1981.

[2]

Albert, Jim. Bayesian Computation with R. Springer Science, New York. Second edition, 2009.

[3]

Bastien, Frédéric, Lamblin, Pascal, Pascanu, Razvan, Bergstra, James, Goodfellow, Ian, Bergeron, Arnaud, Bouchard, Nicolas, Warde-Farley, David, and Bengio, Yoshua. Theano: new features and speed improvements. arXiv preprint arXiv:1211.5590, 2012.

[4]

Dosovitskiy, Alexey, Springenberg, Jost Tobias, and Brox, Thomas. Learning to generate chairs with convolutional neural networks. arXiv preprint arXiv:1411.5928, 2014.

[5]

Gregor, Karol, Danihelka, Ivo, Graves, Alex, and Wierstra, Daan. Draw: A recurrent neural network for image generation. arXiv preprint arXiv:1502.04623, 2015.

[6]

Hinton, Geoffrey E and Zemel, Richard S. Autoencoders, minimum description length, and helmholtz free energy. Advances in neural information processing systems, pp. 3-3, 1994.

[7]

Kingma, Diederik and Ba, Jimmy. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.

[8]

Kingma, Diederik P and Welling, Max. Auto-Encoding Variational Bayes. Proceedings of the 2nd International Conference on Learning Representations, 2014.

[9]

Mnih, Andriy and Gregor, Karol. Neural variational inference and learning in belief networks. In The 31st International Conference on Machine Learning (ICML), 2014.

[10]

Neal, Radford. Mcmc using hamiltonian dynamics. Handbook of Markov Chain Monte Carlo, 2, 2011.

[11]

Paisley, John, Blei, David, and Jordan, Michael. Variational bayesian inference with stochastic search. In Proceedings of the 29th International Conference on Machine Learning (ICML-12), pp. 1367-1374, 2012.

[12]

Ranganath, Rajesh, Gerrish, Sean, and Blei, David. Black box variational inference. In Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, pp. 814-822, 2014.

[13]

Rezende, Danilo J, Mohamed, Shakir, and Wierstra, Daan. Stochastic backpropagation and approximate inference in deep generative models. In Proceedings of the 31st International Conference on Machine Learning (ICML- 14), pp. 1278-1286, 2014.

[14]

Salimans, Tim and Knowles, David A. Fixed-form variational posterior approximation through stochastic linear regression. Bayesian Analysis, 8(4):837-882, 2013.

[15]

Uria, Benigno, Murray, Iain, and Larochelle, Hugo. A deep and tractable density estimator. In Proceedings of the 31th International Conference on Machine Learning, ICML 2014, Beijing, China, 21-26 June 2014, pp. 467-475, 2014. URL http://jmlr.org/proceedings/papers/v32/uria14.html.

Cited By

Becker MLew AWang XGhavami MHuot MRinard MMansinghka V(2024)Probabilistic Programming with Programmable Variational InferenceProceedings of the ACM on Programming Languages10.1145/36564638:PLDI(2123-2147)Online publication date: 20-Jun-2024
https://dl.acm.org/doi/10.1145/3656463
Nehme EYair OMichaeli TOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)Uncertainty quantification via neural posterior principal componentsProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3667735(37128-37141)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3667735
Das AFotiadis SBatra ANabiei FLiao FVakili SShiu DBernacchia AKrause ABrunskill ECho KEngelhardt BSabato SScarlett J(2023)Image generation with shortest path diffusionProceedings of the 40th International Conference on Machine Learning10.5555/3618408.3618687(7009-7024)Online publication date: 23-Jul-2023
https://dl.acm.org/doi/10.5555/3618408.3618687
Show More Cited By

Markov Chain Monte Carlo and variational inference: bridging the gap
1. Computing methodologies
2. Mathematics of computing
  1. Probability and statistics
    1. Probabilistic reasoning algorithms

Recommendations

Variational Bayesian Monte Carlo
NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing Systems

Many probabilistic models of interest in scientific computing and machine learning have expensive, black-box likelihoods that prevent the application of standard techniques for Bayesian inference, such as MCMC, which would require access to the gradient ...
Markov chain Monte Carlo with the Integrated Nested Laplace Approximation

The Integrated Nested Laplace Approximation (INLA) has established itself as a widely used method for approximate inference on Bayesian hierarchical models which can be represented as a latent Gaussian model (LGM). INLA is based on producing an accurate ...
de Finetti Priors using Markov chain Monte Carlo computations

Recent advances in Monte Carlo methods allow us to revisit work by de Finetti who suggested the use of approximate exchangeability in the analyses of contingency tables. This paper gives examples of computational implementations using Metropolis ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

ICML'15: Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37

July 2015

2558 pages

Editors:
Francis Bach,
David Blei

Publisher

JMLR.org

Publication History

Published: 06 July 2015

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

48
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 01 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Becker MLew AWang XGhavami MHuot MRinard MMansinghka V(2024)Probabilistic Programming with Programmable Variational InferenceProceedings of the ACM on Programming Languages10.1145/36564638:PLDI(2123-2147)Online publication date: 20-Jun-2024
https://dl.acm.org/doi/10.1145/3656463
Nehme EYair OMichaeli TOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)Uncertainty quantification via neural posterior principal componentsProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3667735(37128-37141)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3667735
Das AFotiadis SBatra ANabiei FLiao FVakili SShiu DBernacchia AKrause ABrunskill ECho KEngelhardt BSabato SScarlett J(2023)Image generation with shortest path diffusionProceedings of the 40th International Conference on Machine Learning10.5555/3618408.3618687(7009-7024)Online publication date: 23-Jul-2023
https://dl.acm.org/doi/10.5555/3618408.3618687
Peis IMa CHernández-Lobato JKoyejo SMohamed SAgarwal ABelgrave DCho KOh A(2022)Missing data imputation and acquisition with deep Hierarchical models and Hamiltonian Monte CarloProceedings of the 36th International Conference on Neural Information Processing Systems10.5555/3600270.3602867(35839-35851)Online publication date: 28-Nov-2022
https://dl.acm.org/doi/10.5555/3600270.3602867
Chadebec CVincent LAllassonnière SKoyejo SMohamed SAgarwal ABelgrave DCho KOh A(2022)PythaeProceedings of the 36th International Conference on Neural Information Processing Systems10.5555/3600270.3601838(21575-21589)Online publication date: 28-Nov-2022
https://dl.acm.org/doi/10.5555/3600270.3601838
Doucet AGrathwohl WMatthews AStrathmann HKoyejo SMohamed SAgarwal ABelgrave DCho KOh A(2022)Score-based diffusion meets annealed importance samplingProceedings of the 36th International Conference on Neural Information Processing Systems10.5555/3600270.3601831(21482-21494)Online publication date: 28-Nov-2022
https://dl.acm.org/doi/10.5555/3600270.3601831
Chadebec CAllassonnière SKoyejo SMohamed SAgarwal ABelgrave DCho KOh A(2022)A geometric perspective on variational autoencodersProceedings of the 36th International Conference on Neural Information Processing Systems10.5555/3600270.3601696(19618-19630)Online publication date: 28-Nov-2022
https://dl.acm.org/doi/10.5555/3600270.3601696
Taniguchi SIwasawa YKumagai WMatsuo YKoyejo SMohamed SAgarwal ABelgrave DCho KOh A(2022)Langevin autoencoders for learning deep latent variable modelsProceedings of the 36th International Conference on Neural Information Processing Systems10.5555/3600270.3601235(13277-13289)Online publication date: 28-Nov-2022
https://dl.acm.org/doi/10.5555/3600270.3601235
Kuzina AWelling MTomczak JKoyejo SMohamed SAgarwal ABelgrave DCho KOh A(2022)Alleviating adversarial attacks on variational autoencoders with MCMCProceedings of the 36th International Conference on Neural Information Processing Systems10.5555/3600270.3600911(8811-8823)Online publication date: 28-Nov-2022
https://dl.acm.org/doi/10.5555/3600270.3600911
Ritter HKukla MZhang CLi YRanzato MBeygelzimer ADauphin YLiang PVaughan J(2021)Sparse uncertainty representation in deep learning with inducing weightsProceedings of the 35th International Conference on Neural Information Processing Systems10.5555/3540261.3540760(6515-6528)Online publication date: 6-Dec-2021
https://dl.acm.org/doi/10.5555/3540261.3540760
Show More Cited By

View Options

View options

Media

Figures

Other

Tables

View Table of Contents