CS774. Markov Random Field : Theory and Application Lecture 08 Kyomin Jung KAIST Sep 29 2009.

Slides:



Advertisements
Similar presentations
Lecture 9 Support Vector Machines
Advertisements

Factorial Mixture of Gaussians and the Marginal Independence Model Ricardo Silva Joint work-in-progress with Zoubin Ghahramani.
1 LP Duality Lecture 13: Feb Min-Max Theorems In bipartite graph, Maximum matching = Minimum Vertex Cover In every graph, Maximum Flow = Minimum.
Approximation Algorithms Chapter 14: Rounding Applied to Set Cover.
C&O 355 Mathematical Programming Fall 2010 Lecture 22 N. Harvey TexPoint fonts used in EMF. Read the TexPoint manual before you delete this box.: A A A.
Totally Unimodular Matrices
Introduction to Markov Random Fields and Graph Cuts Simon Prince
ICCV 2007 tutorial Part III Message-passing algorithms for energy minimization Vladimir Kolmogorov University College London.
CS774. Markov Random Field : Theory and Application Lecture 17 Kyomin Jung KAIST Nov
by Rianto Adhy Sasongko Supervisor: Dr.J.C.Allwright
An Introduction to Variational Methods for Graphical Models.
Separating Hyperplanes
1 Fast Primal-Dual Strategies for MRF Optimization (Fast PD) Robot Perception Lab Taha Hamedani Aug 2014.
CS774. Markov Random Field : Theory and Application Lecture 04 Kyomin Jung KAIST Sep
Chapter 8-3 Markov Random Fields 1. Topics 1. Introduction 1. Undirected Graphical Models 2. Terminology 2. Conditional Independence 3. Factorization.
CS774. Markov Random Field : Theory and Application Lecture 06 Kyomin Jung KAIST Sep
Visual Recognition Tutorial
Support Vector Machines
Support Vector Machines and Kernel Methods
Approximation Algorithms
Totally Unimodular Matrices Lecture 11: Feb 23 Simplex Algorithm Elliposid Algorithm.
Convergent and Correct Message Passing Algorithms Nicholas Ruozzi and Sekhar Tatikonda Yale University TexPoint fonts used in EMF. Read the TexPoint manual.
Announcements  Homework 4 is due on this Thursday (02/27/2004)  Project proposal is due on 03/02.
Duality Lecture 10: Feb 9. Min-Max theorems In bipartite graph, Maximum matching = Minimum Vertex Cover In every graph, Maximum Flow = Minimum Cut Both.
Support Vector Machine (SVM) Classification
Group Strategyproofness and No Subsidy via LP-Duality By Kamal Jain and Vijay V. Vazirani.
EE 685 presentation Optimization Flow Control, I: Basic Algorithm and Convergence By Steven Low and David Lapsley Asynchronous Distributed Algorithm Proof.
Computability and Complexity 24-1 Computability and Complexity Andrei Bulatov Approximation.
Visual Recognition Tutorial
Lecture 10: Support Vector Machines
Greg GrudicIntro AI1 Support Vector Machine (SVM) Classification Greg Grudic.
CS774. Markov Random Field : Theory and Application Lecture 10 Kyomin Jung KAIST Oct
Approximating Minimum Bounded Degree Spanning Tree (MBDST) Mohit Singh and Lap Chi Lau “Approximating Minimum Bounded DegreeApproximating Minimum Bounded.
CS774. Markov Random Field : Theory and Application Lecture 13 Kyomin Jung KAIST Oct
Planar Cycle Covering Graphs for inference in MRFS The Typhon Algorithm A New Variational Approach to Ground State Computation in Binary Planar Markov.
1 Introduction to Approximation Algorithms. 2 NP-completeness Do your best then.
CS774. Markov Random Field : Theory and Application Lecture 21 Kyomin Jung KAIST Nov
Approximation Algorithms Department of Mathematics and Computer Science Drexel University.
On the Number of Spanning Trees a Planar Graph Can Have Kevin Buchin Andre Schulz ESA 2010, , Reporter : 葉士賢 林建旻 蕭聖穎 張琮勛 賴俊鳴.
Probabilistic Graphical Models
Computational Intelligence: Methods and Applications Lecture 23 Logistic discrimination and support vectors Włodzisław Duch Dept. of Informatics, UMK Google:
Fast and accurate energy minimization for static or time-varying Markov Random Fields (MRFs) Nikos Komodakis (Ecole Centrale Paris) Nikos Paragios (Ecole.
CS774. Markov Random Field : Theory and Application Lecture 02
Markov Chains and Random Walks. Def: A stochastic process X={X(t),t ∈ T} is a collection of random variables. If T is a countable set, say T={0,1,2, …
CSE 589 Part VI. Reading Skiena, Sections 5.5 and 6.8 CLR, chapter 37.
EE 685 presentation Optimization Flow Control, I: Basic Algorithm and Convergence By Steven Low and David Lapsley.
An Introduction to Variational Methods for Graphical Models
Approximate Inference: Decomposition Methods with Applications to Computer Vision Kyomin Jung ( KAIST ) Joint work with Pushmeet Kohli (Microsoft Research)
1 Mean Field and Variational Methods finishing off Graphical Models – Carlos Guestrin Carnegie Mellon University November 5 th, 2008 Readings: K&F:
Linear Program Set Cover. Given a universe U of n elements, a collection of subsets of U, S = {S 1,…, S k }, and a cost function c: S → Q +. Find a minimum.
Lecture 2: Statistical learning primer for biologists
Support Vector Machines
CPSC 536N Sparse Approximations Winter 2013 Lecture 1 N. Harvey TexPoint fonts used in EMF. Read the TexPoint manual before you delete this box.: AAAAAAAAAA.
OR Chapter 7. The Revised Simplex Method  Recall Theorem 3.1, same basis  same dictionary Entire dictionary can be constructed as long as we.
Eric Xing © Eric CMU, Machine Learning Algorithms and Theory of Approximate Inference Eric Xing Lecture 15, August 15, 2010 Reading:
Linear Programming Chapter 9. Interior Point Methods  Three major variants  Affine scaling algorithm - easy concept, good performance  Potential.
Greg GrudicIntro AI1 Support Vector Machine (SVM) Classification Greg Grudic.
Bayesian Belief Propagation for Image Understanding David Rosenberg.
Markov Random Fields in Vision
Theory of Computational Complexity Probability and Computing Ryosuke Sasanuma Iwama and Ito lab M1.
Theory of Computational Complexity Probability and Computing Chapter Hikaru Inada Iwama and Ito lab M1.
Lap Chi Lau we will only use slides 4 to 19
Topics in Algorithms Lap Chi Lau.
The minimum cost flow problem
Chap 9. General LP problems: Duality and Infeasibility
Randomized Algorithms CS648
Analysis of Algorithms
CS5321 Numerical Optimization
An Introduction to Variational Methods for Graphical Models
Locality In Distributed Graph Algorithms
Presentation transcript:

CS774. Markov Random Field : Theory and Application Lecture 08 Kyomin Jung KAIST Sep

Review: Exponential Family Parametrization of positive MRFs, i.e. P[x]>0 for all x. Let denote a collection of potential functions defined on the cliques of G. Let be a vector of weights on these potent ials functions. An MRF with weight is defined by Where the log partition function is

Lemmas So the Hessian of the log partition function Z is equal to a covariance matrix, which is always positive definite.  Hence Z is convex as a function of.

Convex combinations Let denote the set of all spanning trees of G. Let be an exponential parameter vector that represents a tree T, i.e. only for vertices and edges of T. Let be a probability distribution over T(G):

Example 4/ G

Upper bound on the log partition ftn By Jensen’s inequality we obtain that For all and such that Then how to choose and that minimize ?

Upper bound on the log partition ftn Optimizing over with fixed Since Z is convex and the constraint is linear, it has a global minimum, and it could be solved exactly by nonlinear programming. Note : number of spanning tree is large  ex Cayley’s formula says that # of spanning tree of a complete graph is  Hence we will solve the dual problem which has smaller # of variables.

Pseudo-marginals Consider a set of Pseudo-marginals We require the following constraints If G is a tree, LOCAL(G) is a complete description of the set of valid marginals.

Pseudo-marginals Let denote the projection of onto the spanning tree T: Then we can define an MRF

Lagrangian dual Let be the optimal primal solution. And let be the optimal dual solution. Then we have that, for any tree T, Hence, fully expresses for all tree T. Note that has dimension which is small.

Optimal Upper Bound (for fixed ) Where is the single node entropy. is mutual information between and. is the edge appearance prob. of the edge e. …(1)

Optimal Upper Bound (for changing ) Note that for a fixed, only matters. has large dimension (# of spanning trees of G), has small dimension (# of edges of G). is a convex function of. Use Conditional gradient method to compute optimal

Tree reweighted sum-product (for fixed ) Message passing implementation of the dual problem (1). Messages from vertex t to s are defined as follows.

Tree reweighted sum-product The Pseudo-marginals is computed by which maximizes

How the messages are defined Lagrangean associated with (1) is where Take derivatives w.r.t. and to obtain relations (that are used in the message update). Then define the message via

Self Avoiding Walk tree Comparison with computation tree

Self Avoiding Walk tree Theorem  Consider any binary pairwise MRF on a graph G=(V,E). For any vertex v, the marginal prob. computed at the root node of Tsaw(v) is equal to the marginal prob. for v in the original MRF.  Same theorem holds for MAP, i.e. for  Hence Tsaw can be used to compute exact marginal and MAP for graphs with small # of cycles.