May Jun. 2017 Jui.
SunMonTueWedThuFriSat
28293031010203
04 050607080910
11121314151617
18192021 222324
25262728 293001
Click Seminar

Next Seminar

DateJune 29, 2017 (Thursday)
Time10:00-11:00
SpeakerAkihiro Kishimoto 
ProfileResearch Staff Member, IBM Ireland
TitleEfficient AND/OR search algorithms for exact MAP inference task over graphical models 
Abstract
Graphical models provide a powerful framework for reasoning with probabilistic information. Combinatorial maximization, or maximum a posteriori (MAP) tasks arise in many applications and often can be efficiently solved by search schemes, especially in the context of AND/OR search spaces that are sensitive to the underlying problem structure.
In this talk, I present the power of limited memory best-first search over AND/OR search spaces, named RBFAOO, which performs exact MAP inference over graphical models. I also present parallelized versions of RBFAOO which run in both shared-memory and distributed-memory environments. I show that RBFAOO is empirically superior to the current state-of-the-art approaches based on AND/OR search, especially on very hard problem instances.
Site