Corpus ID: 52980921

Block Stability for MAP Inference

@article{Lang2019BlockSF,
  title={Block Stability for MAP Inference},
  author={Hunter Lang and D. Sontag and Aravindan Vijayaraghavan},
  journal={ArXiv},
  year={2019},
  volume={abs/1810.05305}
}
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 are adversarially perturbed. Unfortunately, this strong condition does not seem to hold in practice. We introduce a significantly more relaxed condition that only requires portions of an input instance to be stable. Under this… Expand
Graph cuts always find a global optimum (with a catch)
Bilu-Linial stability, certified algorithms and the Independent Set problem
Graph Cuts Always Find a Global Optimum for Potts Models (With a Catch)

References

SHOWING 1-10 OF 33 REFERENCES
Maximum persistency via iterative relaxed inference with graphical models
Optimality of Approximate Inference Algorithms on Stable Instances
Partial Optimality by Pruning for MAP-Inference with General Graphical Models
Fixing Max-Product: Convergent Message Passing Algorithms for MAP LP-Relaxations
Train and Test Tightness of LP Relaxations in Structured Prediction
Exact MAP-Inference by Confining Combinatorial Search With LP Relaxation
Center-based clustering under perturbation stability
1 Introduction to Dual Decomposition for Inference
A Comparative Study of Modern Inference Techniques for Discrete Energy Minimization Problems
...
1
2
3
4
...