MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models.
Siddharth TouraniAlexander ShekhovtsovCarsten RotherBogdan SavchynskyyPublished in: CoRR (2020)
Keyphrases
- graphical models
- coordinate ascent
- belief propagation
- image recovery
- probabilistic inference
- random variables
- probabilistic graphical models
- probabilistic model
- approximate inference
- bayesian networks
- structure learning
- single processor
- markov networks
- map inference
- conditional independence
- global convergence
- conditional random fields
- factor graphs
- distributed memory
- shared memory
- evolutionary algorithm
- super resolution