From 85d2de4ff3588b8059b2bb45ec9444097b996aa7 Mon Sep 17 00:00:00 2001 From: Thibaut Horel Date: Fri, 6 Feb 2015 18:27:55 -0500 Subject: Typos --- paper/sections/lowerbound.tex | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'paper/sections/lowerbound.tex') diff --git a/paper/sections/lowerbound.tex b/paper/sections/lowerbound.tex index becd13f..a7ae21c 100644 --- a/paper/sections/lowerbound.tex +++ b/paper/sections/lowerbound.tex @@ -4,7 +4,7 @@ support recovery with constant probability under a \emph{correlation decay} assumption. In this section, we will consider the stable sparse recovery setting of Section~\ref{sec:relaxing_sparsity}. Our goal is to obtain an information-theoretic lower bound on the number of measurements necessary to -approximately recover the parameter $\theta$ of a cascade model from observed +approximately recover the parameter $\theta^*$ of a cascade model from observed cascades. Similar lower bounds were obtained for sparse \emph{linear} inverse problems in \cite{pw11, pw12, bipw11}. -- cgit v1.2.3-70-g09d2