This file contains a table of contents of 
"Graphical Models, Exponential Families, and Variational Inference" 
by Wainwright & Jordan, semi-automatically extracted by Wittawat Jitkrittum.
----------------------------------------------------------------------------

Abstract
1 Introduction
2 Background
2.1 Probability Distributions on Graphs
2.2 Conditional Independence
2.3 Statistical Inference and Exact Algorithms
2.4 Applications
2.5 Exact Inference Algorithms
2.6 Message-passing Algorithms for Approximate Inference
3 Graphical Models as Exponential Families
3.1 Exponential Representations via Maximum Entropy
3.2 Basics of Exponential Families
3.3 Examples of Graphical Models in Exponential Form
3.4 Mean Parameterization and Inference Problems
3.5 Properties of A
3.6 Conjugate Duality: Maximum Likelihood and
3.7 Computational Challenges with High-Dimensional
4 Sum-Product, Bethe–Kikuchi, and
4.1 Sum-Product and Bethe Approximation
4.2 Kikuchi and Hypertree-based Methods
4.3 Expectation-Propagation Algorithms
5 Mean Field Methods
5.1 Tractable Families
5.2 Optimization and Lower Bounds
5.3 Naive Mean Field Algorithms
5.4 Nonconvexity of Mean Field
5.5 Structured Mean Field
6 Variational Methods in Parameter Estimation
6.1 Estimation in Fully Observed Models
6.2 Partially Observed Models and
6.3 Variational Bayes
7 Convex Relaxations and Upper Bounds
7.1 Generic Convex Combinations and Convex Surrogates
7.2 Variational Methods from Convex Relaxations
7.3 Other Convex Variational Methods
7.4 Algorithmic Stability
7.5 Convex Surrogates in Parameter Estimation
8 Integer Programming, Max-product, and Linear
8.1 Variational Formulation of Computing Modes
8.2 Max-product and Linear Programming on Trees
8.3 Max-product For Gaussians and Other Convex
8.4 First-order LP Relaxation and Reweighted
8.5 Higher-order LP Relaxations
9 Moment Matrices, Semidefinite Constraints, and
9.1 Moment Matrices and Their Properties
9.2 Semidefinite Bounds on Marginal Polytopes
9.3 Link to LP Relaxations and Graphical Structure
9.4 Second-order Cone Relaxations
10 Discussion

Acknowledgments

Appendix
A Background Material
A.1 Background on Graphs and Hypergraphs
A.2 Basics of Convex Sets and Functions
B Proofs and Auxiliary Results: Exponential
B.1 Proof of Theorem 3.3
B.2 Proof of Theorem 3.4
B.3 General Properties of M and A^*
B.4 Proof of Theorem 4.2(b)
B.5 Proof of Theorem 8.1
C Variational Principles for Multivariate Gaussians
C.1 Gaussian with Known Covariance
C.2 Gaussian with Unknown Covariance
C.3 Gaussian Mode Computation
D Clustering and Augmented Hypergraphs
D.1 Covering Augmented Hypergraphs
D.2 Specification of Compatibility Functions
E Miscellaneous Results
E.1 M¨obius Inversion
E.2 Auxiliary Result for Proposition 9.3
E.3 Conversion to a Pairwise Markov Random Field
References