Corpus ID: 116972835

Approximate inference in graphical models using lp relaxations

@inproceedings{Jaakkola2010ApproximateII,
  title={Approximate inference in graphical models using lp relaxations},
  author={T. Jaakkola and D. Sontag},
  year={2010}
}
Graphical models such as Markov random fields have been successfully applied to a wide variety of fields, from computer vision and natural language processing, to computational biology. Exact probabilistic inference is generally intractable in complex models having many dependencies between the variables. We present new approaches to approximate inference based on linear programming (LP) relaxations. Our algorithms optimize over the cycle relaxation of the marginal polytope, which we show to… Expand
Tighter Linear Program Relaxations for High Order Graphical Models
Belief Propagation for Linear Programming
Tightness Results for Local Consistency Relaxations in Continuous MRFs
Partial Optimality by Pruning for MAP-Inference with General Graphical Models
1 Introduction to Dual Decomposition for Inference
Bottom-Up Approaches to Approximate Inference and Learning in Discrete Graphical Models
MAP Inference via L2-Sphere Linear Program Reformulation
Tighter Relaxations for MAP-MRF Inference: A Local Primal-Dual Gap based Separation Algorithm
Partial Optimality of Dual Decomposition for MAP Inference in Pairwise MRFs
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 136 REFERENCES
Cutting plane algorithms for variational inference in graphical models
Linear Programming Relaxations and Belief Propagation - An Empirical Study
Log-determinant relaxation for approximate inference in discrete Markov random fields
Learning Bayesian Network Structure using LP Relaxations
An LP View of the M-best MAP problem
Using Combinatorial Optimization within Max-Product Belief Propagation
Convex relaxation methods for graphical models: Lagrangian and maximum entropy approaches
Graphical Models, Exponential Families, and Variational Inference
MAP estimation via agreement on trees: message-passing and linear programming
...
1
2
3
4
5
...