See this document in CiteSeerX!

A Mode-Hopping MCMC sampler (2003)  (Make Corrections)  (1 citation)
Cristian Sminchisescu, Max Welling, Geoffrey Hinton



  Home/Search   Context   Related

 
View or download:
toronto.edu/~crismin/PAP...modehop.pdf
Cached:  PS.gz  PS  PDF   Image  Update  Help

From:  toronto.edu/~crism...publications (more)
(Enter author homepages)

Rate this article: (best)
  Comment on this article  
(Enter summary)

Abstract: One of the main shortcomings of Markov chain Monte Carlo samplers is their inability to mix between modes of the target distribution. In this paper we show that advance knowledge of the location of these modes can be incorporated into the MCMC sampler by introducing mode-hopping moves that satisfy detailed balance. The proposed sampling algorithm explores local mode structure through local MCMC moves (e.g. diffusion or Hybrid Monte Carlo) but in addition also represents the relative... (Update)

Similar documents based on text:   More   All
0.2:   Learning Sparse Topographic Representations - With Products Of   (Correct)
0.2:   Kinematic Jump Processes For Monocular 3D Human Tracking - Sminchisescu, Triggs (2003)   (Correct)
0.2:   Incremental Model-Based Estimation Using Geometric.. - Sminchisescu.. (2001)   (Correct)

BibTeX entry:   (Update)

C. Sminchisescu, M. Welling, and G. Hinton. A Mode-Hopping MCMC Sampler. Technical Report CSRG-478, University of Toronto, submitted to Machine Learning Journal, September 2003. 29 http://citeseer.ist.psu.edu/sminchisescu03modehopping.html   More

@misc{ sminchisescu03modehopping,
  author = "C. Sminchisescu and M. Welling and G. Hinton",
  title = "A Mode-Hopping MCMC Sampler",
  text = "C. Sminchisescu, M. Welling, and G. Hinton. A Mode-Hopping MCMC Sampler.
    Technical Report CSRG-478, University of Toronto, submitted to Machine Learning
    Journal, September 2003. 29",
  year = "2003",
  url = "citeseer.ist.psu.edu/sminchisescu03modehopping.html" }
Citations (may not include all citations):
686   Practical Methods of Optimization (context) - Fletcher - 1987
364   CONDENSATION -- Conditional Density Propagation for Visual T.. - Isard, Blake - 1998
199   Probabilistic Inference Using Markov Chain Monte Carlo - Neal - 1993
101   Articulated Body Motion Capture by Annealed Particle Filteri.. (context) - Deutscher, Blake et al. - 2000
84   Hybrid Monte Carlo (context) - Duane, Kennedy et al. - 1987
70   Human Figures Using 2D Image Motion (context) - Sidenbladh, Black et al. - 2000
50   Training Products of Experts by Minimizing Contrastive Diver.. - Hinton - 2002
42   Annealed Importance Sampling - Neal - 1998
42   Annealed Importance Sampling - Neal - 2001
29   Covariance-Scaled Sampling for Monocular 3D Body Tracking - Sminchisescu, Triggs - 2001
25   Implicit Probabilistic Models of Human Motion for Synthesis .. - Sidenbladh, Black et al. - 2002
23   Sampling from multimodal distributions using tempered transi.. - Neal - 1996
22   People Tracking Using Hybrid Monte Carlo Filtering - Choo, Fleet - 2001
11   Adaptive Markov Chain Monte Carlo Through Regeneration - Gilks, Roberts et al. - 1998
10   Kinematic Jump Processes for Monocular 3D Human Tracking - Sminchisescu, Triggs - 2003

[Article contains additional citations not shown here]

Documents on the same site (http://www.cs.toronto.edu/~crismin/publications.html):   More
Hierarchical Skeleton Abstraction - Telea, Sminchisescu, Dickinson   (Correct)
Using Geometric Constraints - Sminchisescu, Metaxas, Dickinson   (Correct)
Covariance Scaled Sampling for Monocular 3D Body Tracking - Sminchisescu, Triggs (2001)   (Correct)

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC