A. Barbos,
F. Caron,
J. F. Giovannelli,
A. Doucet,
Clone MCMC: Parallel High-Dimensional Gaussian Gibbs Sampling, in Advances in Neural Information Processing Systems (NIPS), 2017.
@incollection{Barbos2017,
title = {Clone {MCMC}: Parallel High-Dimensional {G}aussian {G}ibbs Sampling},
author = {Barbos, A. and Caron, F. and Giovannelli, J. F. and Doucet, A.},
booktitle = {Advances in Neural Information Processing Systems (NIPS)},
year = {2017}
}
F. Caron,
W. Neiswanger,
F. Wood,
A. Doucet,
M. Davy,
Generalized Pólya Urn for Time-Varying Pitman-Yor Processes, Journal of Machine Learning Research (JMLR), vol. 18, no. 27, 1–32, 2017.
@article{Caron2017a,
title = {Generalized {P}{\'o}lya Urn for Time-Varying Pitman-Yor Processes},
author = {Caron, F. and Neiswanger, W. and Wood, F. and Doucet, A. and Davy, M.},
journal = {Journal of Machine Learning Research (JMLR)},
year = {2017},
number = {27},
pages = {1-32},
volume = {18}
}
A. Doucet,
C. Holmes,
R. Bardenet,
On Markov chain Monte Carlo Methods for Tall Data, 2017.
@article{doucet2017markov,
title = {On Markov chain Monte Carlo Methods for Tall Data},
author = {Doucet, A and Holmes, CC and Bardenet, R},
year = {2017}
}
A. Bouchard-Côté,
A. Doucet,
A. Roth,
Particle Gibbs Split-Merge Sampling for Bayesian Inference in Mixture Models, Journal of Machine Learning Research, vol. 18, no. 28, 1–39, Apr. 2017.
@article{pg-sm,
author = {Bouchard-C{\^o}t{\'e}, Alexandre and Doucet, Arnaud and Roth, Andrew},
journal = {Journal of Machine Learning Research},
month = apr,
number = {28},
pages = {1--39},
title = {{Particle Gibbs Split-Merge Sampling for Bayesian Inference in Mixture Models}},
volume = {18},
year = {2017}
}
C. J. Maddison,
D. Lawson,
G. Tucker,
N. Heess,
M. Norouzi,
A. Mnih,
A. Doucet,
Y. W. Teh,
Particle Value Functions, in ICLR 2017 Workshop Proceedings, 2017.
The policy gradients of the expected return objective can react slowly to rare rewards. Yet, in some cases agents may wish to emphasize the low or high returns regardless of their probability. Borrowing from the economics and control literature, we review the risk-sensitive value function that arises from an exponential utility and illustrate its effects on an example. This risk-sensitive value function is not always applicable to reinforcement learning problems, so we introduce the particle value function defined by a particle filter over the distributions of an agent’s experience, which bounds the risk-sensitive one. We illustrate the benefit of the policy gradients of this objective in Cliffworld.
@inproceedings{MadLawTuc2017a,
author = {Maddison, C. J. and Lawson, D. and Tucker, G. and Heess, N. and Norouzi, M. and Mnih, A. and Doucet, A. and Teh, Y. W.},
booktitle = {ICLR 2017 Workshop Proceedings},
note = {ArXiv e-prints: 1703.05820},
title = {Particle Value Functions},
year = {2017},
bdsk-url-1 = {https://arxiv.org/pdf/1705.09279v1.pdf}
}
C. J. Maddison,
D. Lawson,
G. Tucker,
N. Heess,
M. Norouzi,
A. Mnih,
A. Doucet,
Y. W. Teh,
Filtering Variational Objectives, in Advances in Neural Information Processing Systems (NIPS), 2017.
The evidence lower bound (ELBO) appears in many algorithms for maximum likelihood estimation (MLE) with latent variables because it is a sharp lower bound of the marginal log-likelihood. For neural latent variable models, optimizing the ELBO jointly in the variational posterior and model parameters produces state-of-the-art results. Inspired by the success of the ELBO as a surrogate MLE objective, we consider the extension of the ELBO to a family of lower bounds defined by a Monte Carlo estimator of the marginal likelihood. We show that the tightness of such bounds is asymptotically related to the variance of the underlying estimator. We introduce a special case, the filtering variational objectives (FIVOs), which takes the same arguments as the ELBO and passes them through a particle filter to form a tighter bound. FIVOs can be optimized tractably with stochastic gradients, and are particularly suited to MLE in sequential latent variable models. In standard sequential generative modeling tasks we present uniform improvements over models trained with ELBO, including some whole nat-per-timestep improvements.
@inproceedings{MadLawTuc2017b,
author = {Maddison, C. J. and Lawson, D. and Tucker, G. and Heess, N. and Norouzi, M. and Mnih, A. and Doucet, A. and Teh, Y. W.},
booktitle = {Advances in Neural Information Processing Systems (NIPS)},
title = {Filtering Variational Objectives},
year = {2017},
bdsk-url-1 = {https://arxiv.org/pdf/1705.09279v1.pdf}
}
@article{bardenet2015markov,
title = {On Markov chain Monte Carlo methods for tall data},
author = {Bardenet, R{\'e}mi and Doucet, Arnaud and Holmes, Chris C.},
journal = {arXiv preprint arXiv:1505.02827},
year = {2015}
}
R. Bardenet,
A. Doucet,
C. Holmes,
Markov chain Monte Carlo and tall data, preprint, 2015.
@article{bardenet2015markow,
title = {Markov chain Monte Carlo and tall data},
author = {Bardenet, R{\'e}mi and Doucet, A and Holmes, C},
journal = {preprint},
year = {2015}
}
T. Lienart,
Y. W. Teh,
A. Doucet,
Expectation Particle Belief Propagation, in Advances in Neural Information Processing Systems (NIPS), 2015.
We propose an original particle-based implementation of the Loopy Belief Propagation (LPB) algorithm for pairwise Markov Random Fields (MRF) on a continuous state space. The algorithm constructs adaptively efficient proposal distributions approximating the local beliefs at each note of the MRF. This is achieved by considering proposal distributions in the exponential family whose parameters are updated iterately in an Expectation Propagation (EP) framework. The proposed particle scheme provides consistent estimation of the LBP marginals as the number of particles increases. We demonstrate that it provides more accurate results than the Particle Belief Propagation (PBP) algorithm of Ihler and McAllester (2009) at a fraction of the computational cost and is additionally more robust empirically. The computational complexity of our algorithm at each iteration is quadratic in the number of particles. We also propose an accelerated implementation with sub-quadratic computational complexity which still provides consistent estimates of the loopy BP marginal distributions and performs almost as well as the original procedure.
@inproceedings{LieTehDou2015a,
author = {Lienart, T. and Teh, Y. W. and Doucet, A.},
booktitle = {Advances in Neural Information Processing Systems (NIPS)},
title = {Expectation Particle Belief Propagation},
year = {2015},
bdsk-url-1 = {http://papers.nips.cc/paper/5674-expectation-particle-belief-propagation},
bdsk-url-2 = {http://papers.nips.cc/paper/5674-expectation-particle-belief-propagation.pdf},
bdsk-url-3 = {http://papers.nips.cc/paper/5674-expectation-particle-belief-propagation-supplemental.zip}
}
2014
R. Bardenet,
A. Doucet,
C. C. Holmes,
Towards scaling up Markov chain Monte Carlo: an adaptive subsampling approach, in Proceedings of the 31st International Conference on Machine Learning (ICML-14), 2014, 405–413.
@inproceedings{bardenet2014towards,
title = {Towards scaling up Markov chain Monte Carlo: an adaptive subsampling approach},
author = {Bardenet, R{\'e}mi and Doucet, Arnaud and Holmes, Chris C.},
booktitle = {Proceedings of the 31st International Conference on Machine Learning (ICML-14)},
pages = {405--413},
year = {2014}
}
R. Bardenet,
A. Doucet,
C. C. Holmes,
An adaptive subsampling approach for MCMC inference in large datasets, in Proceedings of The 31st International Conference on Machine Learning, 2014, 405–413.
@inproceedings{bardenet2014adaptive,
title = {An adaptive subsampling approach for MCMC inference in large datasets},
author = {Bardenet, R{\'e}mi and Doucet, Arnaud and Holmes, Chris C.},
booktitle = {Proceedings of The 31st International Conference on Machine Learning},
pages = {405--413},
year = {2014}
}
B. Paige,
F. Wood,
A. Doucet,
Y. W. Teh,
Asynchronous Anytime Sequential Monte Carlo, in Advances in Neural Information Processing Systems (NIPS), 2014.
We introduce a new sequential Monte Carlo algorithm we call the particle cascade. The particle cascade is an asynchronous, anytime alternative to traditional sequential Monte Carlo algorithms that is amenable to parallel and distributed implementations. It uses no barrier synchronizations which leads to improved particle throughput and memory efficiency. It is an anytime algorithm in the sense that it can be run forever to emit an unbounded number of particles while keeping within a fixed memory budget. We prove that the particle cascade provides an unbiased marginal likelihood estimator which can be straightforwardly plugged into existing pseudo-marginal methods.
@inproceedings{PaiWooDou2014a,
author = {Paige, B. and Wood, F. and Doucet, A. and Teh, Y. W.},
booktitle = {Advances in Neural Information Processing Systems (NIPS)},
title = {Asynchronous Anytime Sequential {M}onte {C}arlo},
year = {2014},
bdsk-url-1 = {http://papers.nips.cc/paper/5450-asynchronous-anytime-sequential-monte-carlo},
bdsk-url-2 = {http://papers.nips.cc/paper/5450-asynchronous-anytime-sequential-monte-carlo.pdf},
bdsk-url-3 = {http://papers.nips.cc/paper/5450-asynchronous-anytime-sequential-monte-carlo-supplemental.zip}
}
2012
A. Lee,
F. Caron,
A. Doucet,
C. C. Holmes,
. others,
Bayesian sparsity-path-analysis of genetic association signal using generalized t priors, Statistical applications in genetics and molecular biology, vol. 11, no. 2, 1–29, 2012.
@article{lee2012bayesian,
title = {Bayesian sparsity-path-analysis of genetic association signal using generalized t priors},
author = {Lee, Anthony and Caron, Francois and Doucet, Arnaud and Holmes, Chris C. and others},
journal = {Statistical applications in genetics and molecular biology},
volume = {11},
number = {2},
pages = {1--29},
year = {2012},
publisher = {Walter de Gruyter GmbH \& Co. KG}
}
2010
A. Lee,
F. Caron,
A. Doucet,
C. C. Holmes,
A hierarchical Bayesian framework for constructing sparsity-inducing priors, arXiv preprint arXiv:1009.1914, 2010.
@article{lee2010hierarchical,
title = {A hierarchical Bayesian framework for constructing sparsity-inducing priors},
author = {Lee, Anthony and Caron, Francois and Doucet, Arnaud and Holmes, Chris C.},
journal = {arXiv preprint arXiv:1009.1914},
year = {2010}
}
A. Lee,
C. Yau,
M. B. Giles,
A. Doucet,
C. C. Holmes,
On the utility of graphics cards to perform massively parallel simulation of advanced Monte Carlo methods, Journal of Computational and Graphical Statistics, vol. 19, no. 4, 769–789, 2010.
@article{lee2010utility,
title = {On the utility of graphics cards to perform massively parallel simulation of advanced Monte Carlo methods},
author = {Lee, Anthony and Yau, Christopher and Giles, Michael B and Doucet, Arnaud and Holmes, Chris C},
journal = {Journal of Computational and Graphical Statistics},
volume = {19},
number = {4},
pages = {769--789},
year = {2010},
publisher = {ASA}
}
2009
F. Caron,
A. Doucet,
Bayesian Nonparametric Models on Decomposable Graphs, in Advances in Neural Information Processing Systems (NIPS), 2009.
@inproceedings{Caron2009,
title = {Bayesian Nonparametric Models on Decomposable Graphs},
author = {Caron, F. and Doucet, A.},
booktitle = {Advances in Neural Information Processing Systems (NIPS)},
year = {2009},
owner = {caron},
timestamp = {2016.10.24}
}
S. Anjum,
A. Doucet,
C. C. Holmes,
A boosting approach to structure learning of graphs with and without prior knowledge, Bioinformatics, vol. 25, no. 22, 2929–2936, 2009.
@article{anjum2009boosting,
title = {A boosting approach to structure learning of graphs with and without prior knowledge},
author = {Anjum, Shahzia and Doucet, Arnaud and Holmes, Chris C},
journal = {Bioinformatics},
volume = {25},
number = {22},
pages = {2929--2936},
year = {2009},
publisher = {Oxford Univ Press}
}
2008
F. Caron,
M. Davy,
A. Doucet,
E. Duflos,
P. Vanheeghe,
Bayesian inference for linear dynamic models with Dirichlet process mixtures, IEEE Transactions on Signal Processing, vol. 56, no. 1, 71–84, 2008.
@article{Caron2008,
title = {Bayesian inference for linear dynamic models with {D}irichlet process mixtures},
author = {Caron, F. and Davy, M. and Doucet, A. and Duflos, E. and Vanheeghe, P.},
journal = {IEEE Transactions on Signal Processing},
year = {2008},
number = {1},
pages = {71--84},
volume = {56},
owner = {caron},
publisher = {IEEE},
timestamp = {2016.10.24}
}
A. Jasra,
A. Doucet,
D. A. Stephens,
C. C. Holmes,
Interacting sequential Monte Carlo samplers for trans-dimensional simulation, Computational Statistics & Data Analysis, vol. 52, no. 4, 1765–1791, 2008.
@article{jasra2008interacting,
title = {Interacting sequential Monte Carlo samplers for trans-dimensional simulation},
author = {Jasra, Ajay and Doucet, Arnaud and Stephens, David A and Holmes, Chris C},
journal = {Computational Statistics \& Data Analysis},
volume = {52},
number = {4},
pages = {1765--1791},
year = {2008},
publisher = {Elsevier}
}
2007
F. Caron,
M. Davy,
A. Doucet,
Generalized Polya urn for time-varying Dirichlet process mixtures, in Uncertainty in Artificial Intelligence (UAI), 2007.
@inproceedings{Caron2007,
title = {{Generalized Polya urn for time-varying Dirichlet process mixtures}},
author = {Caron, F. and Davy, M. and Doucet, A.},
booktitle = {Uncertainty in Artificial Intelligence (UAI)},
year = {2007},
owner = {caron},
timestamp = {2016.10.24}
}