Continuous Relaxation of MAP Inference: A Nonconvex Perspective.
D. Khuê Lê-HuuNikos ParagiosPublished in: CoRR (2018)
Keyphrases
- map inference
- continuous relaxation
- graphical models
- mixed integer
- cutting plane
- knapsack problem
- markov random field
- higher dimensional
- image labeling
- lp relaxation
- optimization problems
- linear programming
- objective function
- convex optimization
- feasible solution
- optimal solution
- maximum a posteriori
- approximation algorithms
- dynamic systems
- markov networks
- structure learning
- convex hull
- probabilistic model
- quadratic program
- high dimensional
- image segmentation