references.bib

@article{offlineEval,
    author    = {Lihong Li and
                 Wei Chu and
                 John Langford},
    title     = {An Unbiased, Data-Driven, Offline Evaluation Method of Contextual
                 Bandit Algorithms},
    journal   = {CoRR},
    volume    = {abs/1003.5956},
    year      = {2010},
    url       = {http://arxiv.org/abs/1003.5956},
    timestamp = {Mon, 05 Dec 2011 18:04:18 +0100},
    biburl    = {http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1003-5956},
    bibsource = {dblp computer science bibliography, http://dblp.org}
}

@article{conBanditNews,
    author    = {Lihong Li and
                 Wei Chu and
                 John Langford and
                 Robert E. Schapire},
    title     = {A Contextual-Bandit Approach to Personalized News Article Recommendation},
    journal   = {CoRR},
    volume    = {abs/1003.0146},
    year      = {2010},
    url       = {http://arxiv.org/abs/1003.0146},
    timestamp = {Mon, 05 Dec 2011 18:05:38 +0100},
    biburl    = {http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1003-0146},
    bibsource = {dblp computer science bibliography, http://dblp.org}
}

@incollection{GLMBandit, 
    Title = {Parametric Bandits: The Generalized Linear Case}, 
    Url = {http://books.nips.cc/papers/files/nips23/NIPS2010_0828.pdf}, 
    Booktitle = {Advances in Neural Information Processing Systems 23}, 
    Author = {Sarah Filippi and Olivier Cappe and Aurélien Garivier and Csaba Szepesvári}, 
    Editor = {J. Lafferty and C. Williams and J. Shawe-taylor and R.s. Zemel and A. Culotta}, 
    Year = {2010}, 
    Pages = {586--594} 
}

@article{thompsonRegret,
    author    = {Shipra Agrawal and
                 Navin Goyal},
    title     = {Further Optimal Regret Bounds for Thompson Sampling},
    journal   = {CoRR},
    volume    = {abs/1209.3353},
    year      = {2012},
    url       = {http://arxiv.org/abs/1209.3353},
    timestamp = {Wed, 10 Oct 2012 21:28:55 +0200},
    biburl    = {http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1209-3353},
    bibsource = {dblp computer science bibliography, http://dblp.org}
}

@Article{UCB,
    author = "Lai, T. L. and Robbins, Herbert",
    title = "Asymptotically Efficient Adaptive Allocation Rules",
    journal = "Advances in Applied Mathematics",
    year = "1985",
    volume = "6",
    number = "1",
    pages = "4--22",
    url = "http://www.cs.utexas.edu/~shivaram",
    bib2html_rescat = "Bandits"
}

@article{Auer2002,
    author = {Auer, Peter and Cesa-Bianchi, Nicol\`{o} and Fischer, Paul},
    title = {Finite-time Analysis of the Multiarmed Bandit Problem},
    journal = {Mach. Learn.},
    issue_date = {May-June 2002},
    volume = {47},
    number = {2-3},
    month = may,
    year = {2002},
    issn = {0885-6125},
    pages = {235--256},
    numpages = {22},
    url = {http://dx.doi.org/10.1023/A:1013689704352},
    doi = {10.1023/A:1013689704352},
    acmid = {599677},
    ublisher = {Kluwer Academic Publishers},
    address = {Hingham, MA, USA},
    keywords = {adaptive allocation rules, bandit problems, finite horizon regret}
} 

@incollection{epochGreedy,
    title = {The Epoch-Greedy Algorithm for Multi-armed Bandits with Side Information},
    author = {Langford, John and Zhang, Tong},
    booktitle = {Advances in Neural Information Processing Systems 20},
    editor = {J.C. Platt and D. Koller and Y. Singer and S.T. Roweis},
    pages = {817--824},
    year = {2008},
    publisher = {Curran Associates, Inc.},
    url = {http://papers.nips.cc/paper/3178-the-epoch-greedy-algorithm-for-multi-armed-bandits-with-side-information.pdf}
}

@misc{pymaBandits,
    author={Olivier Cappe and Aurelien Garivier and Emilie Kaufmann},
    title={pymaBandits},
    year={2012},
    note={\url{http://mloss.org/software/view/415/}}
}

@ARTICLE {subGauss,
    author  = "V. V. Buldygin AND K. K. Moskvichova",
    title   = "The Sub-Gaussian Norm of a Binary Random Variable",
    journal = "Theoretical Probability and Mathematical Statistics",
    year    = "2012",
    number  = "86",
    pages   = "33–49",
    note    = "http://www.ams.org/journals/tpms/2013-86-00/S0094-9000-2013-00887-4/S0094-9000-2013-00887-4.pdf"
}

@article {yahoo,
    author = "Yahoo!",
    title = "Yahoo! Webscope dataset ydata-frontpage-todaymodule-clicks-v1_0",
    note = "http://labs.yahoo.com/Academic_Relations"
}

@InProceedings{precup,
  author =       "Precup, Doina and Sutton, Richard S. and Singh, Satinder P.",
  title =        "Eligibility Traces for Off-Policy Policy Evaluation",
  booktitle =    "Proceedings of the Seventeenth International Conference on Machine Learning (ICML 2000)",
  year =         "2000",
  ISBN =         "1-55860-707-2",
  publisher = "Morgan Kauffman",
  address =   "San Francisco, CA, USA",
  pages =     "759--766",
  url = "http://www.cs.ualberta.ca/~papersdb/uploaded_files/467/paper_PSS-00.pdf",
  bib2html_rescat = "General RL",
}

@Article{LaiRobbins,
  author =       "Lai, T. L. and Robbins, Herbert",
  title =        "Asymptotically Efficient Adaptive Allocation Rules",
  journal =      "Advances in Applied Mathematics",
  year =         "1985",
  volume =    "6",
  number =    "1",
  pages =     "4--22",
  url = "http://www.cs.utexas.edu/~shivaram",
  bib2html_rescat = "Bandits",
}

@article{cappe2013,
    ajournal = "Ann. Statist.",
    author = "Cappé, Olivier and Garivier, Aurélien and Maillard, Odalric-Ambrym and Munos, Rémi and Stoltz, Gilles",
    doi = "10.1214/13-AOS1119",
    journal = "The Annals of Statistics",
    month = "06",
    number = "3",
    pages = "1516--1541",
    publisher = "The Institute of Mathematical Statistics",
    title = "Kullback–Leibler upper confidence bounds for optimal sequential allocation",
    url = "http://dx.doi.org/10.1214/13-AOS1119",
    volume = "41",
    year = "2013"
}

@Article{thompson1933,
    author =       "William R. Thompson",
    title =        "On the Likelihood that One Unknown Probability Exceeds
                   Another in View of the Evidence of Two Samples",
    journal =      j-BIOMETRIKA,
    volume =       "25",
    number =       "3/4",
    pages =        "285--294",
    month =        dec,
    year =         "1933",
    CODEN =        "BIOKAX",
    DOI =          "http://dx.doi.org/10.2307/2332286",
    ISSN =         "0006-3444 (print), 1464-3510 (electronic)",
    ISSN-L =       "0006-3444",
    bibdate =      "Sat Jun 21 14:32:11 MDT 2014",
    bibsource =    "http://www.jstor.org/journals/00063444.html;
                   http://www.jstor.org/stable/i315394;
                   http://www.math.utah.edu/pub/tex/bib/biometrika1930.bib",
    URL =          "http://www.jstor.org/stable/2332286",
    acknowledgement = ack-nhfb,
    fjournal =     "Biometrika",
    journal-URL =  "http://www.jstor.org/journals/00063444.html",
}

@article{conthompson,
  author    = {Shipra Agrawal and Navin Goyal},
  title     = {Thompson Sampling for Contextual Bandits with Linear Payoffs},
  journal   = {CoRR},
  volume    = {abs/1209.3352},
  year      = {2012},
  url       = {http://arxiv.org/abs/1209.3352},
  timestamp = {Wed, 10 Oct 2012 21:28:55 +0200},
  biburl    = {http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1209-3352},
  bibsource = {dblp computer science bibliography, http://dblp.org}
}

@MISC{empthompson,
    author = {Olivier Chapelle and Lihong Li},
    title = {An Empirical Evaluation of Thompson Sampling},
    year = {2011}
}

@INPROCEEDINGS{empiricalbandit,
    author = {Joannès Vermorel and Mehryar Mohri},
    title = {Multi-armed bandit algorithms and empirical evaluation},
    booktitle = {In European Conference on Machine Learning},
    year = {2005},
    pages = {437--448},
    publisher = {Springer}
}

@Book{berry,
    author = { Berry, Donald A. and Fristedt, Bert, },
    title = { Bandit problems : sequential allocation of experiments / Donald A. Berry, Bert Fristedt },
    isbn = { 0412248107 },
    publisher = { Chapman and Hall London ; New York },
    pages = { viii, 275 p. : },
    year = { 1985 },
    type = { Book },
    language = { English },
    subjects = { Experimental design. },
    life-dates = { 1985 -  },
    catalogue-url = { http://nla.gov.au/nla.cat-vn1556352 },
}

@article{ops,
    author = {Farias, Vivek F. and Madan, Ritesh},
    title = {The Irrevocable Multiarmed Bandit Problem},
    journal = {Operations Research},
    volume = {59},
    number = {2},
    pages = {383-399},
    year = {2011},
    doi = {10.1287/opre.1100.0891},
    URL = { http://dx.doi.org/10.1287/opre.1100.0891 },
    eprint = { http://dx.doi.org/10.1287/opre.1100.0891 }
}

@inproceedings{AgarWeb,
 author = {Agarwal, Deepak and Chen, Bee-Chung and Elango, Pradheep},
 title = {Explore/Exploit Schemes for Web Content Optimization},
 booktitle = {Proceedings of the 2009 Ninth IEEE International Conference on Data Mining},
 series = {ICDM '09},
 year = {2009},
 isbn = {978-0-7695-3895-2},
 pages = {1--10},
 numpages = {10},
 url = {http://dx.doi.org/10.1109/ICDM.2009.52},
 doi = {10.1109/ICDM.2009.52},
 acmid = {1677012},
 publisher = {IEEE Computer Society},
 address = {Washington, DC, USA},
 keywords = {multi-armed bandits, web application, content scheduling, Bayes optimal},
} 

@misc{uci,
author = "K. Bache and M. Lichman",
year = "2013",
title = "{UCI} Machine Learning Repository",
url = "http://archive.ics.uci.edu/ml",
institution = "University of California, Irvine, School of Information and Computer Sciences" }

@misc{mloss,
author = "M. Braun, S. Sonnerburg, C.S. Ong",
year = "2014",
title = "Machine Learning Open Source Software",
url = "http://mloss.org",
institution = "ML Group of the TU Berlin" }

@INPROCEEDINGS{ChuConjoint,
    author = {Wei Chu and Seung-taek Park and Todd Beaupre and Nitin Motgi and Amit Phadke and Seinjuti Chakraborty and Joe Zachariah},
    title = {A case study of behavior-driven conjoint analysis on yahoo! front page today module},
    booktitle = {In Proc. of KDD},
    year = {2009}
}