survey.tex

\documentclass{article}
\usepackage[utf8]{inputenc}
\usepackage[margin=1in]{geometry}
\usepackage{amsmath,mathtools,amssymb}

\setlength\parindent{0pt}
\setlength\parskip{4pt}
\title{Unsupervised Methods for Machine Learning \\
\large Clustering \& Crowdsourcing}
\author{Achal Dave, Vaishaal Shankar}
\date{}

\DeclarePairedDelimiter\ceil{\lceil}{\rceil}%
\DeclarePairedDelimiter\floor{\lfloor}{\rfloor}%
\DeclarePairedDelimiter\abs{\lvert}{\rvert}%
\DeclarePairedDelimiter\norm{\lVert}{\rVert}%
\newcommand{\E}{\mathbb{E}}
\newcommand{\R}{\mathbb{R}}
\newcommand{\cA}{\mathcal{A}}
\newcommand{\cL}{\mathcal{L}}
\newcommand{\st}{\text{s.t.}}
\newcommand{\Var}{\mathrm{Var}}
\newcommand \textlcsc[1]{\textsc{\MakeLowercase{#1}}}

\DeclareMathOperator*{\argmin}{arg\!\min}
\DeclareMathOperator*{\argmax}{arg\!\max}
\newtheorem{theorem}{Theorem}[section]
\newtheorem{lemma}[theorem]{Lemma}
\newtheorem{proposition}[theorem]{Proposition}
\newtheorem{corollary}[theorem]{Corollary}

\newenvironment{proof}[1][Proof]{\begin{trivlist}
\item[\hskip \labelsep {\bfseries #1}]}{\end{trivlist}}
\newenvironment{definition}[1][Definition]{\begin{trivlist}
\item[\hskip \labelsep {\bfseries #1}]}{\end{trivlist}}
\newenvironment{example}[1][Example]{\begin{trivlist}
\item[\hskip \labelsep {\bfseries #1}]}{\end{trivlist}}
\newenvironment{remark}[1][Remark]{\begin{trivlist}
\item[\hskip \labelsep {\bfseries #1}]}{\end{trivlist}}

\newcommand{\qed}{\nobreak \ifvmode \relax \else
      \ifdim\lastskip<1.5em \hskip-\lastskip
      \hskip1.5em plus0em minus0.5em \fi \nobreak
      \vrule height0.75em width0.5em depth0.25em\fi}
\input{inputmacros}

\begin{document}


\maketitle
\tableofcontents
\clearpage


\section{Introduction}

This survey focuses on unsupervised machine learning algorithms, and
specifically on their use in problems related to large datasets as found in
modern problems across fields including computer vision, text processing, and
malware detection. The difficulty of obtaining accurate ground truth in these
areas, where a labeling expert is either too expensive or simply does not exists,
makes unsupervised learning algorithms particularly attractive.

In this survey, we will particularly analyze spectral clustering and
crowdsourced labelling.

\section{Spectral Clustering}
\input{clustering}

\newpage

\section{Probabilistic Crowdsourcing}
\input{crowdsourcing}

\bibliographystyle{unsrt}
\bibliography{ref}

\end{document}