WriteupRelWork.bib

@techreport{Zaharia:EECS-2011-82,
    Author = {Zaharia, Matei and Chowdhury, Mosharaf and Das, Tathagata and Dave, Ankur and Ma, Justin and McCauley, Murphy and Franklin, Michael and Shenker, Scott and Stoica, Ion},
    Title = {Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing},
    Institution = {EECS Department, University of California, Berkeley},
    Year = {2011},
    Month = {Jul},
    URL = {http://www.eecs.berkeley.edu/Pubs/TechRpts/2011/EECS-2011-82.html},
    Number = {UCB/EECS-2011-82},
}
@misc{mahout,
author = {{Apache Mahout}},
title = {\url{http://mahout.apache.org/}}
}

@misc{Revolution,
author = {{Revloution Analytics}},
title = {\url{http://www.revolutionanalytics.com/}}
}

@article{ripley2001r,
  title={The {R} project in statistical computing},
  author={Ripley, B.D.},
  journal={MSOR Connections},
  volume={1},
  number={1},
  pages={23--25},
  year={2001}
}

@article{choi1996scalapack,
  title={{ScaLAPACK}: A portable linear algebra library for distributed memory computers -- Design issues and performance},
  author={Choi, J. and Demmel, J. and Dhillon, I. and Dongarra, J. and Ostrouchov, S. and Petitet, A. and Stanley, K. and Walker, D. and Whaley, R.C.},
  journal={Computer Physics Communications},
  volume={97},
  number={1},
  pages={1--15},
  year={1996},
  publisher={Elsevier}
}

@article{gray1997data,
  title={Data cube: A relational aggregation operator generalizing group-by, cross-tab, and sub-totals},
  author={Gray, J. and Chaudhuri, S. and Bosworth, A. and Layman, A. and Reichart, D. and Venkatrao, M. and Pellow, F. and Pirahesh, H.},
  journal={Data Mining and Knowledge Discovery},
  volume={1},
  number={1},
  pages={29--53},
  year={1997},
  publisher={Springer}
}

@inproceedings{wang2011hybrid,
  title={Hybrid in-database inference for declarative information extraction},
  author={Wang, D.Z. and Franklin, M.J. and Garofalakis, M. and Hellerstein, J.M. and Wick, M.L.},
  booktitle={SIGMOD},
  year={2011}
}

@inproceedings{lafferty2001conditional,
 author = {Lafferty, John D. and McCallum, Andrew and Pereira, Fernando C. N.},
 title = {Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data},
 booktitle = {ICML},
 year = {2001},
 pages = {282--289},
}

@article{viterbi,
 title={The viterbi algorithm},
 author={Forney Jr, G.D.},
 journal={Proceedings of the IEEE},
 volume={61},
 number={3},
 pages={268--278},
 year={1973},
 publisher={IEEE}
}

@inproceedings{pavlo2009comparison,
  title={A comparison of approaches to large-scale data analysis},
  author={Pavlo, A. and Paulson, E. and Rasin, A. and Abadi, D.J. and DeWitt, D.J. and Madden, S. and Stonebraker, M.},
  booktitle={SIGMOD},
  pages={165--178},
  year={2009},
  organization={ACM}
}

@incollection{Nedic00,
       Author = {Angelia Nedic and Dimitri P.~Bertsekas},
	Booktitle = {Stochastic Optimization: Algorithms and Applications},
       Editor = {S.~Uryasev and P.~M.~Pardalos},
	Pages = {263--304},
       Publisher = {Kluwer Academic Publishers},
	Title = {Convergence Rate of Incremental Subgradient Algorithms},
       Year = {2000}}

@inproceedings{scalops,
 title={Machine learning in ScalOps, a higher order cloud computing language},
 author={Weimer, M. and Condie, T. and Ramakrishnan, R. and Dror, G. and Koenigstein, N. and Koren, Y. and Weimer, M. and Karatzoglou, A. and Weimer, M. and Zinkevich, M. and others},
 booktitle={NIPS 2011 Workshop on parallel and large-scale machine learning (BigLearn)},
 volume={9},
 pages={389--396},
 year={2011}
}

@inproceedings{hyracks,
  title={Hyracks: A flexible and extensible foundation for data-intensive computing},
  author={Borkar, V. and Carey, M. and Grover, R. and Onose, N. and Vernica, R.},
  booktitle={ICDE},
  pages={1151--1162},
  year={2011}
}

@inproceedings{scidb,
  title={The architecture of {SciDB}},
  author={Stonebraker, M. and Brown, P. and Poliakov, A. and Raman, S.},
  booktitle={Scientific and Statistical Database Management},
  pages={1--16},
  year={2011},
  organization={Springer}
}

@book{JurafskyMartin,
 title={Speech and Language Processing},
 author={Jurafsky, D. and Martin J. H.},
 year={2008},
 publisher={Pearson Prentice Hall}
}


@book{feldman2007text,
 title={The text mining handbook: advanced approaches in analyzing unstructured data},
 author={Feldman, R. and Sanger, J.},
 year={2007},
 publisher={Cambridge Univ Pr}
}

@article{Navarro:2001:GTA:375360.375365,
author = {Navarro, Gonzalo},
title = {A guided tour to approximate string matching},
journal = {ACM Comput. Surv.},
issue_date = {March 2001},
volume = {33},
number = {1},
month = mar,
year = {2001},
issn = {0360-0300},
pages = {31--88},
numpages = {58},
url = {http://doi.acm.org/10.1145/375360.375365},
doi = {10.1145/375360.375365},
acmid = {375365},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {Levenshtein distance, edit distance, online string matching, text searching allowing errors},
}

@book{koller2009probabilistic,
 title={Probabilistic graphical models: principles and techniques},
 author={Koller, D. and Friedman, N.},
 year={2009},
 publisher={The MIT Press}
}

@article{gravano2001using,
 title={Using q-grams in a {DBMS} for Approximate String Processing},
 author={Gravano, L. and Ipeirotis, P.G. and Jagadish, H.V. and Koudas, N. and Muthukrishnan, S. and Pietarinen, L. and Srivastava, D.},
 journal={IEEE Data Engineering Bulletin},
 volume={24},
 number={4},
 pages={28--34},
 year={2001},
 publisher={Citeseer}
}

       
@inproceedings{ordonez-sigmod2000,
 author    = {Carlos Ordonez and
              Paul Cereghini},
 title     = {SQLEM: Fast Clustering in {SQL} using the EM Algorithm},
 booktitle = {SIGMOD},
 year      = {2000},
 pages     = {559-570},
}

@article{ordonez-tkde10,
  author    = {Carlos Ordonez},
  title     = {Statistical Model Computation with UDFs},
  journal   = {IEEE Trans. Knowl. Data Eng.},
  volume    = {22},
  number    = {12},
  year      = {2010},
  pages     = {1752-1765},
  ee        = {http://dx.doi.org/10.1109/TKDE.2010.44},
  bibsource = {DBLP, http://dblp.uni-trier.de}
}

@article{DBLP:journals/tkde/Ordonez06,
  author    = {Carlos Ordonez},
  title     = {Integrating K-Means Clustering with a Relational {DBMS} Using
              {SQL}},
  journal   = {IEEE Trans. Knowl. Data Eng.},
  volume    = {18},
  number    = {2},
  year      = {2006},
  pages     = {188-201},
  ee        = {http://doi.ieeecomputersociety.org/10.1109/TKDE.2006.31},
  bibsource = {DBLP, http://dblp.uni-trier.de}
}       
       
@misc{vw,
author={John Langford},
title={\url{http://hunch.net/~vw/}}
}

@misc{ORE,
author = {{Oracle R Enterprise}},
title = {\url{http://www.oracle.com/technetwork/database/options/advanced-analytics/r-enterprise/index.html}}
}

@inproceedings{Ricardo:Das:2010:RIR:1807167.1807275,
 author = {Das, Sudipto and Sismanis, Yannis and Beyer, Kevin S. and Gemulla, Rainer and Haas, Peter J. and McPherson, John},
 title = {Ricardo: integrating R and Hadoop},
 booktitle = {Proceedings of the 2010 international conference on Management of data},
 series = {SIGMOD '10},
 year = {2010},
 isbn = {978-1-4503-0032-2},
 location = {Indianapolis, Indiana, USA},
 pages = {987--998},
 numpages = {12},
 url = {http://doi.acm.org/10.1145/1807167.1807275},
 doi = {10.1145/1807167.1807275},
 acmid = {1807275},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {analytics, cloud, data management, hadoop, r, statistics},
} 

@inproceedings{SystemML:Ghoting:2011:SDM:2004686.2005625,
 author = {Ghoting, Amol and Krishnamurthy, Rajasekar and Pednault, Edwin and Reinwald, Berthold and Sindhwani, Vikas and Tatikonda, Shirish and Tian, Yuanyuan and Vaithyanathan, Shivakumar},
 title = {SystemML: Declarative machine learning on MapReduce},
 booktitle = {Proceedings of the 2011 IEEE 27th International Conference on Data Engineering},
 series = {ICDE '11},
 year = {2011},
 isbn = {978-1-4244-8959-6},
 pages = {231--242},
 numpages = {12},
 url = {http://dx.doi.org/10.1109/ICDE.2011.5767930},
 doi = {10.1109/ICDE.2011.5767930},
 acmid = {2005625},
 publisher = {IEEE Computer Society},
 address = {Washington, DC, USA},
} 

@article{SNOW:Tierney:2009:SPC:1598913.1598918,
 author = {Tierney, Luke and Rossini, A. J. and Li, Na},
 title = {Snow: a parallel computing framework for the R system},
 journal = {Int. J. Parallel Program.},
 issue_date = {February 2009},
 volume = {37},
 number = {1},
 month = feb,
 year = {2009},
 issn = {0885-7458},
 pages = {78--90},
 numpages = {13},
 url = {http://dx.doi.org/10.1007/s10766-008-0077-2},
 doi = {10.1007/s10766-008-0077-2},
 acmid = {1598918},
 publisher = {Kluwer Academic Publishers},
 address = {Norwell, MA, USA},
 keywords = {MPI, PVM, bootstrap, cross-validation, distributed memory, message passing, sockets},
} 

@article{MADlib:Cohen:2009:MSN:1687553.1687576,
 author = {Cohen, Jeffrey and Dolan, Brian and Dunlap, Mark and Hellerstein, Joseph M. and Welton, Caleb},
 title = {MAD skills: new analysis practices for big data},
 journal = {Proc. VLDB Endow.},
 issue_date = {August 2009},
 volume = {2},
 number = {2},
 month = aug,
 year = {2009},
 issn = {2150-8097},
 pages = {1481--1492},
 numpages = {12},
 url = {http://dl.acm.org/citation.cfm?id=1687553.1687576},
 acmid = {1687576},
 publisher = {VLDB Endowment},
} 

@article{bismarck,
    author={Xixuan Feng and Arun Kumar and Ben Recht and Christopher R{\'e}},
    title={Towards a Unified Architecture for in-{RDBMS} Analytics},
    journal={SIGMOD},
    year={2012}
}

@article{Tuffy:Niu:2011:TSU:1978665.1978669,
 author = {Niu, Feng and R{\'e}, Christopher and Doan, AnHai and Shavlik, Jude},
 title = {Tuffy: scaling up statistical inference in Markov logic networks using an {RDBMS}},
 journal = {Proc. VLDB Endow.},
 issue_date = {March 2011},
 volume = {4},
 number = {6},
 month = mar,
 year = {2011},
 issn = {2150-8097},
 pages = {373--384},
 numpages = {12},
 url = {http://dl.acm.org/citation.cfm?id=1978665.1978669},
 acmid = {1978669},
 publisher = {VLDB Endowment},
} 

@ARTICLE{Felix:2011arXiv1108.0294N,
author = {{Niu}, F. and {Zhang}, C. and {R{\'e}}, C. and {Shavlik}, J.},
title = {Felix: Scaling Inference for Markov Logic with an Operator-based Approach},
journal = {ArXiv e-prints},
archivePrefix = {arXiv},
eprint = {1108.0294},
primaryClass = {cs.CL},
keywords = {Computer Science - Computation and Language, Computer Science - Databases},
year = 2011,
month = aug,
adsurl = {http://adsabs.harvard.edu/abs/2011arXiv1108.0294N},
adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}

@inproceedings{Dryad:Yu:2008:DSG:1855741.1855742,
 author = {Yu, Yuan and Isard, Michael and Fetterly, Dennis and Budiu, Mihai and Erlingsson, \'{U}lfar and Gunda, Pradeep Kumar and Currey, Jon},
 title = {DryadLINQ: a system for general-purpose distributed data-parallel computing using a high-level language},
 booktitle = {Proceedings of the 8th USENIX conference on Operating systems design and implementation},
 series = {OSDI'08},
 year = {2008},
 location = {San Diego, California},
 pages = {1--14},
 numpages = {14},
 url = {http://dl.acm.org/citation.cfm?id=1855741.1855742},
 acmid = {1855742},
 publisher = {USENIX Association},
 address = {Berkeley, CA, USA},
} 

@inproceedings{Pregel:Malewicz:2010:PSL:1807167.1807184,
 author = {Malewicz, Grzegorz and Austern, Matthew H. and Bik, Aart J.C and Dehnert, James C. and Horn, Ilan and Leiser, Naty and Czajkowski, Grzegorz},
 title = {Pregel: a system for large-scale graph processing},
 booktitle = {SIGMOD},
 year = {2010},
 pages = {135--146},
} 

@inproceedings{Graphlab:conf/uai/LowGKBGH10,
  added-at = {2011-12-15T00:00:00.000+0100},
  author = {Low, Yucheng and Gonzalez, Joseph and Kyrola, Aapo and Bickson, Danny and Guestrin, Carlos and Hellerstein, Joseph M.},
  booktitle = {UAI},
  editor = {Grünwald, Peter and Spirtes, Peter},
  ee = {http://uai.sis.pitt.edu/displayArticleDetails.jsp?mmnu=1&smnu=2&article_id=2126&proceeding_id=26},
  interhash = {15a1c9cddadef854afe21ec56a73a502},
  intrahash = {3f0eff8b2bcc015496052fbb373dafaa},
  isbn = {978-0-9749039-6-5},
  keywords = {dblp},
  pages = {340-349},
  title = {GraphLab: A New Framework For Parallel Machine Learning.},
  year = 2010
}