Simple Instances of Swendson-Wang & RJMCMC

Slides:



Advertisements
Similar presentations
Pattern Recognition and Machine Learning
Advertisements

Pattern Recognition and Machine Learning
Bayesian Belief Propagation
Linear Time Methods for Propagating Beliefs Min Convolution, Distance Transforms and Box Sums Daniel Huttenlocher Computer Science Department December,
Computer vision: models, learning and inference Chapter 18 Models for style and identity.
Ch 11. Sampling Models Pattern Recognition and Machine Learning, C. M. Bishop, Summarized by I.-H. Lee Biointelligence Laboratory, Seoul National.
Proportion Priors for Image Sequence Segmentation Claudia Nieuwenhuis, etc. ICCV 2013 Oral.
EE462 MLCV Lecture Introduction of Graphical Models Markov Random Fields Segmentation Tae-Kyun Kim 1.
Smoothing 3D Meshes using Markov Random Fields
Image Parsing: Unifying Segmentation and Detection Z. Tu, X. Chen, A.L. Yuille and S-C. Hz ICCV 2003 (Marr Prize) & IJCV 2005 Sanketh Shetty.
BAYESIAN INFERENCE Sampling techniques
CS774. Markov Random Field : Theory and Application Lecture 16 Kyomin Jung KAIST Nov
1 Hierarchical Image-Motion Segmentation using Swendsen-Wang Cuts Adrian Barbu Siemens Corporate Research Princeton, NJ Acknowledgements: S.C. Zhu, Y.N.
Particle filters (continued…). Recall Particle filters –Track state sequence x i given the measurements ( y 0, y 1, …., y i ) –Non-linear dynamics –Non-linear.
Face Processing System Presented by: Harvest Jang Group meeting Fall 2002.
Crash Course on Machine Learning
Introduction to Monte Carlo Methods D.J.C. Mackay.
Bayes Factor Based on Han and Carlin (2001, JASA).
Methods in Medical Image Analysis Statistics of Pattern Recognition: Classification and Clustering Some content provided by Milos Hauskrecht, University.
Presenter : Kuang-Jui Hsu Date : 2011/5/23(Tues.).
1 Naïve Bayes Models for Probability Estimation Daniel Lowd University of Washington (Joint work with Pedro Domingos)
Bayesian Inversion of Stokes Profiles A.Asensio Ramos (IAC) M. J. Martínez González (LERMA) J. A. Rubiño Martín (IAC) Beaulieu Workshop ( Beaulieu sur.
Markov Random Fields Probabilistic Models for Images
Max-Margin Classification of Data with Absent Features Presented by Chunping Wang Machine Learning Group, Duke University July 3, 2008 by Chechik, Heitz,
Fields of Experts: A Framework for Learning Image Priors (Mon) Young Ki Baik, Computer Vision Lab.
Bayesian Reasoning: Tempering & Sampling A/Prof Geraint F. Lewis Rm 560:
23 November Md. Tanvir Al Amin (Presenter) Anupam Bhattacharjee Department of Computer Science and Engineering,
Mixture of Gaussians This is a probability distribution for random variables or N-D vectors such as… –intensity of an object in a gray scale image –color.
MCMC (Part II) By Marc Sobel. Monte Carlo Exploration  Suppose we want to optimize a complicated distribution f(*). We assume ‘f’ is known up to a multiplicative.
Lecture 2: Statistical learning primer for biologists
1 Chapter 8: Model Inference and Averaging Presented by Hui Fang.
The Unscented Particle Filter 2000/09/29 이 시은. Introduction Filtering –estimate the states(parameters or hidden variable) as a set of observations becomes.
CS Statistical Machine learning Lecture 25 Yuan (Alan) Qi Purdue CS Nov
RECITATION 2 APRIL 28 Spline and Kernel method Gaussian Processes Mixture Modeling for Density Estimation.
Computational Physics (Lecture 10) PHY4370. Simulation Details To simulate Ising models First step is to choose a lattice. For example, we can us SC,
SIR method continued. SIR: sample-importance resampling Find maximum likelihood (best likelihood × prior), Y Randomly sample pairs of r and N 1973 For.
Naive Bayes (Generative Classifier) vs. Logistic Regression (Discriminative Classifier) Minkyoung Kim.
PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 1: INTRODUCTION.
Generalization Performance of Exchange Monte Carlo Method for Normal Mixture Models Kenji Nagata, Sumio Watanabe Tokyo Institute of Technology.
Markov Chain Monte Carlo in R
Fast search for Dirichlet process mixture models
MCMC Output & Metropolis-Hastings Algorithm Part I
Optimization of Monte Carlo Integration
Computational Physics (Lecture 10)
GEOGG121: Methods Monte Carlo methods, revision
Advanced Statistical Computing Fall 2016
Answering ‘Where am I?’ by Nonlinear Least Squares
Sublinear Computational Time Modeling in Statistical Machine Learning Theory for Markov Random Fields Kazuyuki Tanaka GSIS, Tohoku University, Sendai,
Intro to Sampling Methods
ERGM conditional form Much easier to calculate delta (change statistics)
Ch3: Model Building through Regression
Accelerated Sampling for the Indian Buffet Process
STEREO MATCHING USING POPULATION-BASED MCMC
Machine Learning Basics
Jun Liu Department of Statistics Stanford University
School of Electrical and
Probabilistic Models for Linear Regression
A special case of calibration
Markov chain monte carlo
Remember that our objective is for some density f(y|) for observations where y and  are vectors of data and parameters,  being sampled from a prior.
Graduate School of Information Sciences, Tohoku University
Advanced Statistical Computing Fall 2016
Finite Element Surface-Based Stereo 3D Reconstruction
Image Parsing & DDMCMC. Alan Yuille (Dept. Statistics. UCLA)
Monte Carlo Methods in Scientific Computing
Graduate School of Information Sciences, Tohoku University
Robust Full Bayesian Learning for Neural Networks
Image Segmentation.
Ensemble forecasts and seasonal precipitation tercile probabilities
Stochastic Methods.
Presentation transcript:

Simple Instances of Swendson-Wang & RJMCMC Daniel Eaton CPSC 540 December 13, 2005

A Pedagogical Project (1/1) Two algorithms implemented: 1. SW for image denoising 2. RJMCMC for model selection in a regression problem (in real-time!) Similar to Frank Dellaert’s demo at ICCV 2005 13/12/2005 Daniel Eaton

Swendson-Wang for Denoising (1/8) Denoising problem input: Original image Thresholded + Zero-mean noise 13/12/2005 Daniel Eaton

Swendson-Wang for Denoising (2/8) Model: Ising prior Smoothness: a priori expect neighbouring pixels to be the same Likelihood 13/12/2005 Daniel Eaton

Swendson-Wang for Denoising (3/8) Sampling from posterior Easy: using Hastings algorithm Propose to flip value at single pixel (i,j) Accept with probability Ratio has simple expression involving # of disagreeing edges before/after flip 13/12/2005 Daniel Eaton

Swendson-Wang for Denoising (4/8) Problem: convergence is slow Many steps needed to fill this hole, since update locations are chosen uniformly at random! 13/12/2005 Daniel Eaton

Swendson-Wang for Denoising (5/8) SW to the rescue Flip whole chunks of the image at once BUT Make this a reversible Metropolis-Hastings step so that we are still sampling from right posterior One step 13/12/2005 Daniel Eaton

Swendson-Wang for Denoising (6/8) Hastings SW 13/12/2005 Daniel Eaton

Swendson-Wang for Denoising (7/8) Demo: Hastings VS. SW Hastings allowed to iterate more often than SW to account for difference in computational cost 13/12/2005 Daniel Eaton

Swendson-Wang for Denoising (8/8) Conclusion: SW ill-suited for this task Discriminative edge probabilities very important to convergence Makes large steps at start (if initialization is uniform) but slows near convergence (in presence of small disconnected regions) – ultimately, becomes single-site update algorithm Extra parameter to tune/anneal Does what it claims to – energy is minimized faster than with Hastings alone 13/12/2005 Daniel Eaton

RJMCMC for Regression (1/5) Data randomly generated from a line on [-1,1] with zero-mean Gaussian noise 13/12/2005 Daniel Eaton

RJMCMC for Regression (2/5) Allow two models to compete at explaining this data (uniform prior over models) 1. Linear (parameters: slope & y-intercept) 2. Constant (parameters: offset) 13/12/2005 Daniel Eaton

RJMCMC for Regression (3/5) Heavy-handedly solve simple model selection problem with RJMCMC Recall: ensuring reversibility is one (convenient) way of constructing a MC having the posterior we want to sample from as its invariant distribution RJMCMC/TDMCMC is just a formalism for ensuring reversibility for proposals that jump between models of varying dimension (constant – 1 param., linear – 2 params.) 13/12/2005 Daniel Eaton

RJMCMC for Regression (4/5) Given initial starting conditions (model type, parameters), chain has two types of moves: 1. Parameter update (probability 0.6) Within current model, propose new parameters (Gaussian proposal) and accept with ordinary Hastings ratio 2. Model change (probability 0.4) Propose a model swap If going from constant->linear, uniformly sample a new slope Accept with special RJ ratio (see me/my tutorial for details) 13/12/2005 Daniel Eaton

RJMCMC for Regression (5/5) Model selection: approximate marginal likelihood by number of samples from each model If the model is better at explaining the data, the chain will spend more time using it Demo: 13/12/2005 Daniel Eaton

Questions? Thanks for listening I’ll be happy to answer any questions over a beer later tonight! 13/12/2005 Daniel Eaton