Convergence Rate Analysis of MAP Coordinate Minimization Algorithms
Author(s)
Meshi, Ofer; Jaakkola, Tommi; Globerson, Amir
DownloadPublished version (333.8Kb)
Terms of use
Metadata
Show full item recordAbstract
Finding maximum a posteriori (MAP) assignments in graphical models is an important task in many applications. Since the problem is generally hard, linear programming (LP) relaxations are often used. Solving these relaxations efficiently is thus an important practical problem. In recent years, several authors have proposed message passing updates corresponding to coordinate descent in the dual LP. However, these are generally not guaranteed to converge to a global optimum. One approach to remedy this is to smooth the LP, and perform coordinate descent on the smoothed dual. However, little is known about the convergence rate of this procedure. Here we perform a thorough rate analysis of such schemes and derive primal and dual convergence rates. We also provide a simple dual to primal mapping that yields feasible primal solutions with a guaranteed rate of convergence. Empirical evaluation supports our theoretical claims and shows that the method is highly competitive with state of the art approaches that yield global optima.
Date issued
2012Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence LaboratoryCitation
Meshi, Ofer, Jaakkola, Tommi and Globerson, Amir. 2012. "Convergence Rate Analysis of MAP Coordinate Minimization Algorithms."
Version: Final published version