latex 入门及使用
>> vim test.tex
documentclass[11pt,twoside,a4paper]{article} usepackage{CJKutf8} % 支持中文楷体 usepackage{indentfirst} % 首行缩进２空格 usepackage{multicol} % 两列 usepackage{amsmath,amssymb} % 支持数学公式 usepackage{latexsym} usepackage{geometry} ％ 页边距等设置 geometry{left=2cm,right=2cm,bottom=3cm,top=2.5cm} setlength{parskip}{10pt} % 段落间距
enewcommand{ aggedright}{leftskip=0pt ightskip=0pt plus 0cm}
author{WeiHong Miao \ small{School of Computer Science and Technology Sun Yat-sen University,GuangZhou,510006}} itle {COM: a Generative Model for Group Recommendation } date {September 05,2015} % 正文开始 egin{document} maketitle egin{CJK*}{UTF8}{gkai} egin{multicols}{2} egin{abstract} With the rapd development of online social networks,a growing number of people are willing th share their goup activites,e.g.,having dinners with colleagues,and watching movies with spouses.This motivates the studies on group recommendation,which aims to recommend items for a group of users.Goup recommendation is a challenging problem because different group members have different preferences,hand how to make a trade-off among their preferences for recommendation is still an open problem. par extbf{Categories and Subject Descriptors} [Information Search and Retrieval]: Information Filtering par extbf{Keywords} CRF,Collaborative Filtering,Topic Models,Word2vec end{abstract} section{introduction} par Recommender systems(RS) aim to suggest items for users based on their preferences,and they have been widely deployed to asist users to select items in various fields,such as movies(Netflix),products(Tmall), restaurants(Yelp), etc.A number of recommendation techniques have been proposed,such as user/itembeased collaborative filtering(CF)cite{DK1,DK2},clustering CF[24],matirx factorization[11],etc.,and most of them focus on producting recommedndations for individual users.However,people often participate in activities together with others,e.g.,having dinners with colleagues,watching movies with spouses. $ int _a^b f(x)dx $ 处理楷体字 section {related work} we first briefly review recommendation systems in general,and then focus on techniques for group recommendation. subsection{Recommender Systems} Recommender systems can be classified into threee categories:content-based,collatborative filterging(CF),and hybrid recommendation approaches[1].The content-based approaches make recommendations based on the content features of users(e.g.,age,gender,etc.) subsection{Group recommendation} Recommender systems can be classified into threee categories:content-based,collatborative filterging(CF),and hybrid recommendation approaches[1].The content-based approaches make recommendations based on for various domains,such as web/news pages,tourism,restaruants,music,TV programs. ldots which has serveral advatages. egin{equation} I_D = I_F - I-R end{equation} ldots section{Consensus model} We first define the group recommendation problem in section 3.1,and then introduce the proposed consensus model(COM) in section 3.2.After that the inference algorithm and the recommendation method are presentd in Section 3..3 and 3.4,respecitively.Finally,we present how to incorporate content information into the model in section 3.5.All the notations used in this paper are listed in Table1. subsection{consensus model for group recommendation} par Recommender systems can be classified into threee categories:content-based,collatborative filterging(CF),and hybrid recommendation approaches[1].The content-based approaches make recommendations based on subsection{Problem Statement}Let U,I,G be the user,item and group sets,respectively. A group g Recommender systems can be classified into threee categories:content-based,collatborative filterging(CF),and hybrid recommendation approaches[1].The content-based approaches make recommendations based on. subsection {Word Mover's Distance} paragraph{nBOW representation.} We can think of the vectord as a point on the n-1 dimentsional simplesx of word distributions.Tw3o documents with different unique words will lie in different regions of this simplex.However paragraph{Word travel cost.} Our goal is to incorporate the semantic similarity between indival word pairs(e.g President an Obama) into the document distance metri into the document distance metricc \ extbf {Word travel cost.} Our goal is to incorporate the semantic similarity between indival word pairs(e.g President an Obama) into the document distance metri into the document distance metricc extbf {Word travel cost.} Our goal is to incorporate the semantic similarity between indival word pairs(e.g President an Obama) into the document distance metri into the document distance metricc \ subsection{ Parameter Estimation} some math formulars: Fraction $$frac{a}{b}$$ Power $$ a^b $$ Subscript $a_b$ Derivation $frac{partial y}{partial t}$ Vector $vec{n}$ Bold $mathbf{n} $ To time differential $dot{F}$ Matrix (lcr here means left, center or right for each column) [ left[ egin{array}{lcrcc} a1 & b2 & c333 &jk & fjsjk \ d444 & e555555 & f6 &jksasld & fjkas end{array} ight] ] \ Equations egin{align} a+b &= c \ d+gjsk &= e+f+g end{align} [ left{ egin{aligned} &a+b=c\ &d=e+f+g end{aligned} ight. ] egin{center} egin{tabular}{|c|c|} hline a & b \ hline c & d \ hline end{tabular} end{center} egin{thebibliography}{123456} ibitem{DK1} JK.Miao sysu,T.A.O.C.P.,Vol.1,Addison-Wesley,1997. ibitem{DK2} fhsdakfasdj end{thebibliography} end{multicols} end{CJK*} end{document}
>> pdflatex test.tex
>> evince test.tex