X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=elbo.tex;h=fe91565f8fa6d21c72fee5ef2b87de8006efc3b3;hb=05c0721d2f8b578a8a27ed2085dc9812d2249f88;hp=239a657f8c438ebf50e970b52d049c2b22a5b498;hpb=43b0cb04eae4537d95775038d9e700e642087d6d;p=tex.git

diff --git a/elbo.tex b/elbo.tex
index 239a657..fe91565 100644
--- a/elbo.tex
+++ b/elbo.tex
@@ -91,7 +91,7 @@ Fran\c cois Fleuret
 
 \end{center}
 
-Given a training set $x_1, \dots, x_N$ that follows an unknown
+Given i.i.d training samples $x_1, \dots, x_N$ that follows an unknown
 distribution $\mu_X$, we want to fit a model $p_\theta(x,z)$ to it,
 maximizing
 %
@@ -99,7 +99,7 @@ maximizing
 \sum_n \log \, p_\theta(x_n).
 \]
 %
-If we do not have a analytical form of the marginal $p_\theta(x_n)$
+If we do not have an analytical form of the marginal $p_\theta(x_n)$
 but only the expression of $p_\theta(x_n,z)$, we can get an estimate
 of the marginal by sampling $z$ with any distribution $q$
 %