diff options
| author | Thibaut Horel <thibaut.horel@gmail.com> | 2012-10-25 15:00:16 -0700 |
|---|---|---|
| committer | Thibaut Horel <thibaut.horel@gmail.com> | 2012-10-25 15:00:16 -0700 |
| commit | 93c362fe4dbbeb1cb381fe68af4ca821f215d6a3 (patch) | |
| tree | d86ad357c6aceae041c2d9f3f2b374a974c280fe /paper.tex | |
| parent | d10dc2546f2ffade3e8b4ec360f03f186e8b2282 (diff) | |
| download | recommendation-93c362fe4dbbeb1cb381fe68af4ca821f215d6a3.tar.gz | |
Add paper.tex, beginning of the paper.
Diffstat (limited to 'paper.tex')
| -rw-r--r-- | paper.tex | 48 |
1 files changed, 48 insertions, 0 deletions
diff --git a/paper.tex b/paper.tex new file mode 100644 index 0000000..466ee8e --- /dev/null +++ b/paper.tex @@ -0,0 +1,48 @@ +\documentclass{acm_proc_article-sp} +\usepackage[utf8]{inputenc} +\usepackage{amsmath,amsfonts} +\usepackage{algorithm} +\usepackage{algpseudocode} +\newtheorem{lemma}{Lemma} +\newtheorem{fact}{Fact} +\newtheorem{example}{Example} +\newtheorem{prop}{Proposition} +\newtheorem{theorem}{Theorem} +\newcommand*{\defeq}{\stackrel{\text{def}}{=}} +\newcommand{\var}{\mathop{\mathrm{Var}}} +\newcommand{\condexp}[2]{\mathop{\mathbb{E}}\left[#1|#2\right]} +\newcommand{\expt}[1]{\mathop{\mathbb{E}}\left[#1\right]} +\newcommand{\norm}[1]{\lVert#1\rVert} +\newcommand{\tr}[1]{#1^*} +\newcommand{\ip}[2]{\langle #1, #2 \rangle} +\newcommand{\mse}{\mathop{\mathrm{MSE}}} +\DeclareMathOperator{\trace}{tr} +\DeclareMathOperator*{\argmax}{arg\,max} +\title{Budgeted mechanism for optimal experiment design} +\begin{document} + +\section{Intro} + +\begin{itemize} + \item already existing field of experiment design: survey-like setup, what + are the best points to include in your experiment. Measure of the + usefulness of the data: variance-reduction or entropy-reduction + \item nowadays, there is also a big focus on purchasing data: paid surveys, + mechanical turk, etc. that add economic aspects to the problem of + experiment desgin + \item recent advances (Singer, Chen) in the field of budgeted mechanisms + \item we study ridge regression, very widely used in statistical learning, + and treat it as a problem of budgeted experiment design + \item we make the following contributions: ... + \item extension to a more general setup which includes a wider class of + machine learning problems +\end{itemize} + +\section{Problem formulation} + +\section{Main result} + +\section{General setup} + +\section{Conclusions} +\end{document} |
