源自:http://www.stats.ox.ac.uk/~doucet/samsi_course.html
*
* Slides of the NIPS tutorial
Objectives
To provide an introduction to SMC methods and their applications.- Lecture 1
- Introduction & Motivation
- Lecture 2
- Importance Sampling & Sequential Importance Sampling
Additional reading:
- Kong, Liu & Wong, Sequential imputation and Bayesian missing data problems, JASA, 1994
- Lecture 3
- Sequential Importance Sampling Resampling
- Doucet, De Freitas and Gordon, An introduction to Sequential Monte Carlo, in SMC in Practice, 2001
- Gordon, Salmond & Smith, Novel approach to nonlinear non-Gaussian Bayesian state estimation, IEE, 1993
Matlab code for linear Gaussian example: Kalman + prior and locally optimal proposal
- Lecture 4
- Advanced Sequential Monte Carlo methods
Tutorial
-
Or if you prefer reading the original papers....
Auxiliary particle filters
- M.K. Pitt and N. Shephard, Filtering via Simulation: Auxiliary Particle Filter, JASA, 1999
- A. Johansen and A. Doucet, A Note on Auxiliary Particle Filters, Stat. Proba. Letters, 2008.
Resample move
- W. Gilks and C. Berzuini, Following a moving target: Monte Carlo inference for dynamic Bayesian models, JRSS B, 2001 Pdf file here
Fixed lag sampling
- A. Doucet et al., Efficient Block Sampling Strategies for Sequential Monte Carlo", (with M. Briers & S. Senecal), JCGS,
Variance reduction
- C. Andrieu and A. Doucet, Particle Filtering for Partially Observed Gaussian State Space Models, JRSS B, 2002.
- R. Chen and J. Liu, Mixture Kalman filters, JRSSB, 2000.
- A. Doucet, S.J. Godsill and C. Andrieu, On Sequential Monte Carlo sampling methods for Bayesian filtering, (section IV) Stat. Comp., 2000
- Lecture 5
- Sequential Parameter Estimation for State-Space models: Bayesian and ML approaches
-
Bayesian approaches
* C. Andrieu, N. De Freitas and A. Doucet, Sequential MCMC for Bayesian Model Selection, Proc. IEEE Workshop HOS, 1999
* P. Fearnhead, MCMC, sufficient statistics and particle filters, JCGS, 2002
* G. Storvik,
Non-Bayesian approaches
* C. Andrieu, A. Doucet and V.B. Tadic, Online EM for parameter estimation in nonlinear-non Gaussian state-space models, Proc. IEEE CDC, 2005
* G. Poyadjis, A. Doucet and S.S. Singh,
* P. Del Moral, A. Doucet & S.S. Singh, Forward Smoothing using Sequential Monte Carlo , technical report, Cambridge University, 2009
Application of recursive maximum likelihood
* C. Caron, R. Gottardo and A. Doucet, On-line Changepoint Detection and Parameter Estimation for Genome Wide Transcript Analysis, Technical report 2008
*
- Lecture 6 - Guest Lecturer: Christophe Andrieu
- Adaptive Markov chain Monte Carlo methods
- Lecture 7
- Sequential Monte Carlo Samplers
- Lecture 8 - Guest Lecturer: Alexandre Chorin.
Final Projects
You will have to study a few papers on a specific SMC topic, write a report, implement some algorithms and make a presentation.
Potential projects are listed
References
Basic Introduction to SMC for state-space models* A. Doucet, N. De Freitas and N.J. Gordon, An introduction to Sequential Monte Carlo,
"Standard" SMC papers
* J. Carpenter, P. Clifford and P. Fearnhead,
* A. Doucet, S.J. Godsill and C. Andrieu, On Sequential Monte Carlo sampling methods for Bayesian filtering, Stat. Comp., 2000 (reprinted 2005)
* M.K. Pitt and N. Shephard, Filtering via Simulation: Auxiliary Particle Filter, JASA, 1999
*
SMC papers for sequential static parameter estimation in state-space models
-
* C. Andrieu, N. De Freitas and A. Doucet, Sequential MCMC for Bayesian Model Selection, Proc. IEEE Workshop HOS, 1999
* P. Fearnhead, MCMC, sufficient statistics and particle filters, JCGS, 2002
* G. Storvik,
-
* P. Del Moral, A. Doucet & S.S. Singh, Forward Smoothing using Sequential Monte Carlo , technical report, Cambridge University, 2009
* G. Poyadjis, A. Doucet and S.S. Singh,
* C. Andrieu, A. Doucet and V.B. Tadic, Online EM for parameter estimation in nonlinear-non Gaussian state-space models, Proc. IEEE CDC, 2005
* G. Poyadjis, A. Doucet and S.S. Singh, Maximum Likelihood Parameter Estimation using Particle Methods, Joint Statistical Meeting, 2005
SMC papers for off-line static parameter estimation in state-space models
*
Books discussing extensively SMC methods
* Del Moral, Feynman-Kac Formulae, Springer-Verlag, 2004 - All you want to know about the theory of SMC.
* Doucet, De Freitas & Gordon (eds), Sequential Monte Carlo in Practice, Springer-Verlag: 2001 - A collection of chapters on the subject.
* Cappe, Moulines & Ryden, Inference in Hidden Markov Models, Springer-Verlag, 2005 - Discuss at length the applications of SMC to state-space models
* Liu, Monte Carlo Methods in Scientific Computing, Springer-Verlag, 2001 - Discuss SMC and also MCMC.
Books discussing MCMC (for those not familiar with this class of methods)
* Robert & Casella, Monte Carlo Statistical Methods, 2004.