From 3f3630af30845ab7f305638f6cc2a80abb8435f5 Mon Sep 17 00:00:00 2001 From: jeanpouget-abadie Date: Thu, 5 Feb 2015 11:12:15 -0500 Subject: small changes --- paper/sections/results.tex | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'paper/sections') diff --git a/paper/sections/results.tex b/paper/sections/results.tex index 46521ed..95a0826 100644 --- a/paper/sections/results.tex +++ b/paper/sections/results.tex @@ -164,8 +164,7 @@ Choosing $\lambda\defeq 2\sqrt{\frac{\log m}{\alpha n^{1-\delta}}}$ concludes th proof. \end{proof} -Note how the proof of Lemma 3 relied crucially on Azuma-Hoeffding's inequality: by supposing ... We now show how to use Theorem~\ref{thm:main} to recover the support of -$\theta^*$, that is, to solve the Graph Inference problem. +Note how the proof of Lemma~\ref{lem:ub} relied crucially on Azuma-Hoeffding's inequality, which allows us to handle correlated observations, and obtain bounds on the number of measurements rather than the number of cascades. We now show how to use Theorem~\ref{thm:main} to recover the support of $\theta^*$, that is, to solve the Graph Inference problem. \begin{corollary} \label{cor:variable_selection} -- cgit v1.2.3-70-g09d2