diff options
| author | jeanpouget-abadie <jean.pougetabadie@gmail.com> | 2015-02-04 18:43:17 -0500 |
|---|---|---|
| committer | jeanpouget-abadie <jean.pougetabadie@gmail.com> | 2015-02-04 18:43:17 -0500 |
| commit | 2fae935154432f930b0e9978687996f2f11ae0d5 (patch) | |
| tree | 5347dc0d72f40b3189ee2bae4568af1f009365e0 | |
| parent | a1cf7e1d258f68f9daac4599f6841d8639927e31 (diff) | |
| download | cascades-2fae935154432f930b0e9978687996f2f11ae0d5.tar.gz | |
fixing tiny bug
| -rw-r--r-- | paper/sections/results.tex | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/paper/sections/results.tex b/paper/sections/results.tex index 6e67058..bb31f79 100644 --- a/paper/sections/results.tex +++ b/paper/sections/results.tex @@ -77,7 +77,7 @@ Before moving to the proof of Theorem~\ref{thm:main}, note that interpreting it in the case of the Independent Cascade Model requires one more step. Indeed, to cast it as a generalized linear cascade model, we had to perform the transformation $\Theta_{i,j} = \log(1-p_{i,j})$, where $p_{i,j}$ are the -infection probabilities. Fortunately, if we estimate $p_j}$ through +infection probabilities. Fortunately, if we estimate $p_j$ through $\hat{p}_{j} = \hat{\theta}_j$, a bound on $\|\hat\theta - \theta^*\|_2$ directly implies a bound on $\|\hat p - p^*\|$. Indeed we have: |