AD^3: alternating directions dual decomposition for MAP inference in graphical models

MaRDI QIDQ5502118zbMATH OpenFDO

Authors André F. T. Martins, Mário A. T. Figueiredo, Pedro M. Q. Aguiar, Noah A. Smith, Eric P. Xing

Publication date 17 August 2015

Full work available at URL http://jmlr.csail.mit.edu/papers/v16/martins15a.html

zbMATH Keywords

alternating directions method of multipliersdual decompositiongraphical modelsMAP inferencemaximum a posteriori inference

Mathematics Subject Classification ID

Graphical methods in statistics (62A09) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Discrete graphical models -- an optimization perspective
• Energy distribution view for monotonic dual decomposition
• Variational algorithms for marginal MAP
• scientific article; zbMATH DE number 6253910
• MAP inference via _2-sphere linear program reformulation

Cited in

(10)

• Efficient semidefinite branch-and-cut for MAP-MRF inference
• MAP inference via _2-sphere linear program reformulation
• A biclustering approach based on factor graphs and the max-sum algorithm
• Energy distribution view for monotonic dual decomposition
• Variational algorithms for marginal MAP
• Inference on highly-connected discrete graphical models with applications to visual object recognition
• A tutorial on dual decomposition and Lagrangian relaxation for inference in natural language processing
• Hinge-loss Markov random fields and probabilistic soft logic
• Discrete graphical models -- an optimization perspective
• MAP inference algorithms without approximation for collective graphical models on path graphs via discrete difference of convex algorithm

Describes a project that uses

Uses Software

• GraphLab
• Penn Treebank

This page was built for publication: \(\mathrm{AD}^3\): alternating directions dual decomposition for MAP inference in graphical models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5502118)