Sciweavers

Share
ICML
2010
IEEE

Accelerated dual decomposition for MAP inference

10 years 5 months ago
Accelerated dual decomposition for MAP inference
Approximate MAP inference in graphical models is an important and challenging problem for many domains including computer vision, computational biology and natural language understanding. Current state-of-theart approaches employ convex relaxations of these problems as surrogate objectives, but only provide weak running time guarantees. In this paper, we develop an approximate inference algorithm that is both efficient and has strong theoretical guarantees. Specifically, our algorithm is guaranteed to converge to an -accurate solution of the convex relaxation in O 1 time. We demonstrate our approach on synthetic and real-world problems and show that it outperforms current stateof-the-art techniques.
Vladimir Jojic, Stephen Gould, Daphne Koller
Added 09 Nov 2010
Updated 09 Nov 2010
Type Conference
Year 2010
Where ICML
Authors Vladimir Jojic, Stephen Gould, Daphne Koller
Comments (0)
books