From 7f6b960702e38cf2e34d5594ba2b37a45f8a9520 Mon Sep 17 00:00:00 2001
From: Thibaut Horel <thibaut.horel@gmail.com>
Date: Thu, 12 Dec 2013 17:48:03 -0500
Subject: Reimport things from the appendix to the main part for the
 camera-ready version

---
 conclusion.tex | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'conclusion.tex')

diff --git a/conclusion.tex b/conclusion.tex
index 6b17237..4db1030 100755
--- a/conclusion.tex
+++ b/conclusion.tex
@@ -5,7 +5,7 @@ polynomial time. %Our objective function, commonly known as the Bayes $D$-optima
 A natural question to ask is to what extent ou results
 %we present here
 generalize to other machine learning tasks beyond linear regression. We outline
-a path to such a generalization in Appendix~\ref{sec:ext}: %. In
+a path to such a generalization in \cite{arxiv}: %. In
 %particular, although the information gain is not generally a submodular
 %function, we show that 
 for a wide class of models in which experiment
-- 
cgit v1.2.3-70-g09d2