Block Stability for MAP Inference
© 2019 by the author(s). Recent work (Lang et al., 2018) has shown that some popular approximate MAP inference algorithms perform very well when the input instance is stable. The simplest stability condition assumes that the MAP solution does not change at all when some of the pairwise potentials ar...
Main Authors: | Lang, Hunter, Sontag, David, Vijayaraghavan, Aravindan |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
Format: | Article |
Language: | English |
Published: |
2021
|
Online Access: | https://hdl.handle.net/1721.1/137589 |
Similar Items
-
Perturbation stability for approximate MAP inference
by: Lang, Hunter(Hunter J.)
Published: (2019) -
Tree block coordinate descent for map in graphical models
by: Sontag, David Alexander, et al.
Published: (2011) -
Cutting plane algorithms for variational inference in graphical models
by: Sontag, David Alexander
Published: (2008) -
Approximate inference in graphical models using LP relaxations
by: Sontag, David Alexander
Published: (2011) -
Bayesian inference with optimal maps
by: El Moselhy, Tarek A., et al.
Published: (2015)