Lecture 20 Notes

Lecture 20 Notes - 15-780 Grad AI Lecture 20 Monte Carlo...

Info iconThis preview shows pages 1–20. Sign up to view the full content.

View Full Document Right Arrow Icon
15-780: Grad AI Lecture 20: Monte Carlo methods, Bayesian learning Geoff Gordon (this lecture) Tuomas Sandholm TAs Erik Zawadzki, Abe Othman
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Admin Reminder: midterm March 29 Tuomas’s review session tomorrow, mine yesterday Reminder: project milestone reports due March 31
Background image of page 2
Review: factor graphs Undirected, bipartite graph one set of nodes represents variables other set represents factors in probability distribution—tables of nonnegative numbers need to compute normalizer in order to do anything useful Can convert back and forth to Bayes nets Hard v. soft constraints
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Review: factor graphs Graphical test for independence different results from Bayes net, even if we are representing the same distribution Inference by dynamic programming instantiate evidence, eliminate nuisance nodes, normalize, answer query elimination order matters treewidth Relation to logic
Background image of page 4
Review: HMMs, DBNs Inference over time same graphical template repeated once for each time step—conceptually inFnite Inference: forward- backward algorithm (special case of belief propagation)
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Review: numerical integration Integrate a difFcult function over a high- dimensional volume narrow, tall peaks contribute most of the integral—difFcult search problem Central problem for approximate inference e.g., computing normalizing constant in a factor graph
Background image of page 6
Uniform sampling ï 1 ï 0.5 0 0.5 1 0 10 20 30 40 50 60 70 2 N ° i f ( x i )
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Importance sampling ï 1 ï 0.5 0 0.5 1 0 10 20 30 40 50 60 70
Background image of page 8
Variance How does this help us control variance? Suppose f big ==> Q big And Q small ==> f small Then h = f/Q never gets too big Variance of each sample is lower ==> need fewer samples A good Q makes a good IS
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Importance sampling, part II Suppose f ( x )= R ( x ) g ( x ) ° f ( x ) dx = ° R ( x ) g ( x ) dx = E R [ g ( x )]
Background image of page 10
Importance sampling, part II Use importance sampling w/ proposal Q(X): Pick N samples x i from Q(X) Average w i g(x i ), where w i = R(x i )/Q(x i ) is importance weight E Q ( Wg ( X )) = ° Q ( x ) R ( x ) Q ( x ) g ( x ) = ° R ( x ) g ( x ) dx = ° f ( x ) dx
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Parallel IS Now suppose R(x) is unnormalized (e.g., represented by factor graph)—know only Z R(x) Pick N samples x i from proposal Q(X) If we knew w i = R(x i )/Q(x i ), could do IS Instead, set ˆ w i = ZR ( x i ) /Q ( x i )
Background image of page 12
Parallel IS So, is an unbiased estimate of Z ¯ w = 1 N ° i ˆ w i E ( ˆ W )= ° Q ( x ) ZR ( x ) Q ( x ) dx = ° ( x ) dx = Z
Background image of page 13

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Parallel IS So, is an estimate of w i , computed without knowing Z Final estimate: ˆ w i / ¯ w f ( x ) dx 1 n ± i ˆ w i ¯ w g ( x i )
Background image of page 14
Parallel IS is biased 0 1 2 3 0 0.5 1 1.5 2 2.5 3 mean(weights) 1 / mean(weights) E(mean(weights)) E ( ¯ W )= Z , but E (1 / ¯ W ) ° =1 /Z in general
Background image of page 15

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
ï 2 ï 1 0 1 2 ï 2 ï 1 0 1 2 Q :( X,Y ) N (1 , 1) θ U ( π , π ) f ( x,y, θ )= Q ( θ ) P ( o =0 . 8 | θ ) /Z
Background image of page 16
ï 2 ï 1 0 1 2 ï 2 ï 1 0 1 2 Posterior E ( X,Y, θ ) = (0 . 496 , 0 . 350 , 0 . 084)
Background image of page 17

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
MCMC
Background image of page 18
Integration problem Recall: wanted And therefore, wanted good importance distribution Q(x) (close to R) f ( x ) dx = R ( x ) g ( x ) dx
Background image of page 19

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 20
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

Page1 / 66

Lecture 20 Notes - 15-780 Grad AI Lecture 20 Monte Carlo...

This preview shows document pages 1 - 20. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online