diff options
| -rw-r--r-- | notes/ICML/icml2015stylefiles/paper_v1.tex | 37 |
1 files changed, 37 insertions, 0 deletions
diff --git a/notes/ICML/icml2015stylefiles/paper_v1.tex b/notes/ICML/icml2015stylefiles/paper_v1.tex index 8865e51..8c666cc 100644 --- a/notes/ICML/icml2015stylefiles/paper_v1.tex +++ b/notes/ICML/icml2015stylefiles/paper_v1.tex @@ -77,12 +77,49 @@ blabla \section{Introduction} +\begin{itemize} +\item Small introduction about problem +\item What is a cascade? +\item What is our objective? +\item Motivation for the problem. +\item Summary of our approach +\end{itemize} + +Parameters of the model: +\begin{itemize} +\item $p_{init}$ : multi-source: explain why more reasonable +\item $p_{min}$ +\item $p_i <$ 1- epsilon? +\end{itemize} + \section{Related Work} \subsection{Past work} +\begin{itemize} +\item Gomez +\item Netrapalli: $d^2 $log n + correlation decay + very bad dependence on +\item Kleinberg/Abrahao: $d^9$ log n: single source model... +\item Gomez: $d^3$ log n + assumptions on Hessian of diffusion process: upper and lower bound on eigenvalues + same proof concept as Netrapalli +\end{itemize} + \subsection{Our contribution} +\begin{itemize} +\item Better assumptions: easy to understand, verify?, and much less restrictive +\item Oracle inequality rather than support recovery -> First one +\item Algorithm for recovery in Omega(d log n) -> First one +\item Practical Confidence Intervals +\item Practical Lower bound +\item Compare on generic networks +\end{itemize} + +To justify: +\begin{itemize} +\item why discrete isn't so bad; +\item why Gomez's assumptions are not reasonable; +\end{itemize} + \section{Algorithm and Theoretical Guarantees} \subsection{Independent Cascade Model} |