Upload
dustin-hall
View
240
Download
1
Embed Size (px)
DESCRIPTION
Daphne Koller MAP ≠ Max over Marginals Joint distribution – P(a 0, b 0 ) = 0.04 – P(a 0, b 1 ) = 0.36 – P(a 1, b 0 ) = 0.3 – P(a 1, b 1 ) = 0.3 B AB0B0 B1B1 a0a a1a1 0.5 I a0a0 a1a P(B|A)P(A) A B
Citation preview
Daphne Koller
Maximum a Posteriori (MAP)• Evidence: E=e • Query: all other variables Y (Y={X1,…,Xn}-E)• Task: compute MAP(Y|E=e) = argmaxy P(Y=y | E=e)
– Note: there may be more than one possible solution
• Applications– Message decoding: most likely transmitted message– Image segmentation: most likely segmentation
Daphne Koller
MAP ≠ Max over Marginals• Joint distribution– P(a0, b0) = 0.04– P(a0, b1) = 0.36– P(a1, b0) = 0.3– P(a1, b1) = 0.3
BA B0 B1
a0 0.1 0.9a1 0.5 0.5
Ia0 a1
0.4 0.6
P(B|A)P(A)
A
B
Daphne Koller
NP-HardnessThe following are NP-hard• Given a PGM P, find the joint assignment x with highest probability P(x)
• Given a PGM P and a probability p, decide if there is an assignment x such that P(x) > p
Daphne Koller
Algorithms: MAP• Push maximization into factor product– Variable elimination
• Message passing over a graph–Max-product belief propagation
• Using methods for integer programming• For some networks: graph-cut methods• Combinatorial search
Daphne Koller
Summary• MAP: single coherent assignment of
highest probability– Not the same as maximizing individual
marginal probabilities• Maxing over factor product• Combinatorial optimization problem• Many exact and approximate algorithms