Problems

17.1 Let

μ:=E[f(x)]=f(x)p(x)dx

si172_e

and q(x) be the proposal distribution. Show that if

w(x):=p(x)q(x),

si173_e

and

μ^=1Ni=1Nw(xi)f(xi),

si174_e

then the variance

σf2=Eμ^Eμ^2=1Nf2(x)p2(x)q(x)dxμ2.

si175_e

Observe that if f2(x)p2(x) goes to zero slower than q(x), then for fixed N, σf2.

17.2 In importance sampling, with weights defined as

w(x)=ϕ(

Get Machine Learning now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.