Convergence Rate Analysis of MAP Coordinate Minimization Algorithms
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, severa...
Main Authors: | Meshi, Ofer, Jaakkola, Tommi, Globerson, Amir |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
Format: | Article |
Language: | English |
Published: |
2021
|
Online Access: | https://hdl.handle.net/1721.1/137615 |
Similar Items
-
Convergence Rate Analysis of MAP Coordinate Minimization Algorithms
by: Meshi, Ofer, et al.
Published: (2022) -
More data means less inference: A pseudo-max approach to structured learning
by: Sontag, David, et al.
Published: (2011) -
Learning efficiently with approximate inference via dual losses
by: Meshi, Ofer, et al.
Published: (2011) -
Tree block coordinate descent for map in graphical models
by: Sontag, David Alexander, et al.
Published: (2011) -
On the convergence of the coordinate descent method for convex differentiable minimization
Published: (2003)