@TechReport{Ali1995,
  author =   {Kamal M. Ali},
  title =    {A comparison of methods for learning and combining
                  evidence from multiple models},
  institution =  {Dept of information and computer science, University
                  of California, Irvine},
  year =     1995
}

@ARTICLE{Ferguson73,
  AUTHOR       = {T. Ferguson},
  TITLE        = {A Bayesian Analysis of Some Non-Parametric Problems},
  YEAR         = {1973},
  JOURNAL      = {The Annals of Statistics},
  volume       = {1}
}
@ARTICLE{Neal2000,
  AUTHOR       = {Radford Neal},
  TITLE        = {Markov Chain Sampling Methods for Dirichlet Process Mixture Model},
  YEAR         = {2000},
  JOURNAL      = {Journal of Computational and Graphical Statistics},
  volume       = {9},
}
@ARTICLE{Blackwell73,
  AUTHOR       = {D. Blackwell and J. MacQueen},
  TITLE        = {Ferguson Distributions via Polya Urn Schemes},
  YEAR         = {1973},
  JOURNAL      = {The Annals of Statistics},
  volume       = {1},
}
@ARTICLE{Antoniak74,
  AUTHOR       = {C. Antoniak},
  TITLE        = {Mixture of Dirichlet Processes with Applications to Bayesian Non-Parametric Problems},
  YEAR         = {1974},
  JOURNAL      = {The Annals of Statistics},
  volume       = {2},
}
@ARTICLE{Escobar95,
  AUTHOR       = {M. Escobar and M. West},
  TITLE        = {Bayesian Density Estimation and Inference Using Mixtures},
  YEAR         = {1995},
  JOURNAL      = {Journal of the American Statistical Association},
  volume       = {90},
}

@inproceedings{Allwein00,
  author =   {Erin L. Allwein and Robert E. Schapire and Yoram Singer},
  title =    {Reducing Multiclass to Binary: A Unifying Approach for Margin Classifiers},
  booktitle =    {Intenational Conference on Machine Learning},
  year =     2000
}

@PhdThesis{Joachims2000,
  author =   {Thorsten Joachims},
  title =    {The Maximum Margin Approach to Learning Text Classifiers Methods, Theory and Algorithms},
  school =   {Dortmund University},
  year =     2000
}

@ARTICLE{Haussler1992,
  AUTHOR       = {David Haussler},
  TITLE        = {Decision Theoretic Generalizations of the {PAC} Model for Neural Net and Other Learning Applications},
  YEAR         = {1992},
  JOURNAL      = {Information and Computation},
  volume       = {100},
}


@Article{Amari2000a,
  author =   {Shunichi Amari},
  title =    {Estimating Functions of independent component analysis
for temporally correlated signals},
  journal =      {Neural Computation},
  year =     2000,
  volume =   12
}

@Article{Amari1999,
  author =   {Shunichi Amari},
  title =    {Natural Gradient for over and under-complete bases in {ICA}},
  journal =      {Neural Computation},
  year =     1999,
  volume =   11
}

@Article{Amari1995,
  author =   {S. Amari},
  title =    {Information Geometry of the {EM} and {em} algorithms for neural networks},
  journal =      {Neural Networks},
  year =     1995,
  volume =   8,
  number =   9,
  pages =    {1379-1408}
}

@Book{Amari2000,
  author =   {Shunichi Amari and Hiroshi Nagaoka},
  title =    {Methods of Information Geometry},
  publisher =    {American Mathematical Society},
  year =     2000
}

@InProceedings{Aslam01,
  author =   {J. A. Aslam and M. Montague},
  title =    {Models for Metasearch},
  booktitle =    {Proc. of the ACM SIGIR conference},
  year =     2001
}

@Article{Beran1977,
  author =   {R. Beran},
  title =    {Minimum Hellinger Distance Estimates for Parameteric Models},
  journal =      {Annals of Statistics},
  year =     1977,
  volume =   5,
  number =   3,
  pages =    {445-463}
}





@inproceedings{Berger99,
  author =   {A. Berger},
  title =    {Error-correcting output coding for text classification},
  booktitle =    {IJCAI'99: Workshop on machine learning for information filtering},
  year =     2000
}

@Book{Bishop1975,
  author =   {Y. Bishop and S. Fienberg and P. Holland},
  title =    {Discrete multivariate analysis: theory and practice},
  publisher =    {The MIT press},
  year =     {1975}
}
@Book{Boothby2003,
  author =   {W. M. Boothby},
  title =    {An Introduction to Differentiable Manifolds and Riemannian Geometry},
  publisher =    {Academic Press},
  year =     2003
}

@InProceedings{Breese1998,
  author =   {J. Breese and D. Heckerman and C. Kadie},
  title =    {Empirical analysis of predictive algorithms for collaborative filtering},
  booktitle =    {Proceedings of the 14th Conference on Uncertainty in Artificial Intelligence},
  year =     {1998}
}

@article{Breiman1996,
    author = "Leo Breiman",
    title = "Bagging Predictors",
    journal = "Machine Learning",
    volume = 24,
    number = 2,
    pages = "123-140",
    year = 1996,
}
@Book{Bridson1999,
  author =   {Martin Bridson and Andr\'e Haefliger},
  title =    {Metric Spaces of Non-Positive Curvature},
  publisher =    {Springer},
  year =     1999,
  volume =   319,
  series =   {A Series in Comprehensive Studies in Mathematics}
}
@Article{Bruce1999,
  author =   {Rebecca F. Bruce and Janyce Weibe },
  title =    {Decomposable modeling in natural language processing},
  journal =      {Computational Linguistics},
  year =     1999
}

@Article{Amari1998,
  author =   {Shunichi Amari},
  title =    {Natural Gradient Works Efficiently in Learning},
  journal =      {Neural Computation},
  year =     1998,
  volume =   10
}

@Article{Campbell86,
  author =   {L. L. Campbell},
  title =    {An extended \v{C}encov Characterization of the information metric},
  journal =      {Proceedings of the {American} {Mathematical} {Society}},
  year =     1986,
  volume =   98,
  number =   1,
  pages =    {135-141}
}

@article{Aizerman:64,
  author = {Mark A. Aizerman and Emmanuel M. Braverman and Lev I. Rozono\'{e}r},
  title = "Theoretical foundations of the potential function method in pattern
          recognition and learning",
  journal = "Automation and Remote Control",
  volume = "25",
  year = "1964",
  pages = "821--837",
}

@article{Kimeldorf:71,
  author = {George Kimeldorf and Grace Wahba},
  title = {Some results on {T}chebychean spline functions},
  journal = {J. Math. Anal. Applic.},
  volume = {33},
  year = {1971},
  pages = {82--95},
}
@inproceedings{KondorLafferty:02,
  author = "Risi Imre Kondor and John Lafferty",
  title = "Diffusion kernels on graphs and other discrete input spaces",
  booktitle = "Proceedings of the International Conference on Machine Learning (ICML)",
  editor    = "C. Sammut and A. Hoffmann",
  publisher = "Morgan Kaufmann",
  year = "2002",
}
@inproceedings{Ponte:98a,
title = "A language modeling approach to information retrieval",
author = "Jay Ponte and W.~Bruce Croft ",
booktitle = "Proceedings of the ACM SIGIR",
year = "1998",
pages = "275--281"}

@inproceedings{Zhai:01a,
title = "A Study of Smoothing Methods for Language Models Applied to Ad Hoc Information Retrieval",
author = "Chengxiang Zhai and John Lafferty ",
booktitle = "Proceedings of SIGIR'2001",
location = "New Orleans, LA",
month = "Sept",
year = "2001",
pages = "334--342"}

@inproceedings{Boser:92,
    author = "Bernhard E. Boser and Isabelle Guyon and Vladimir Vapnik",
    title = "A Training Algorithm for Optimal Margin Classifiers",
    booktitle = "Computational Learing Theory",
    pages = "144-152",
    year = "1992",
}
@Article{Campbell1985,
  author =   {L. L. Campbell},
  title =    {The Relation Between Information Theory and the Differential Geometry Approach to Statistics},
  journal =      {Information Sciences},
  year =     1985,
  volume =   35
}

@TechReport{Chen1998,
  author =   {Stanley Chen and Joshua Goodman},
  title =    {An empirical study of smoothing techniques for language modelling},
  institution =  {Harvard university},
  year =     1998
}

@Article{Chen2000,
  author =   {S. Chen and R. Rosenfeld},
  title =    {A survey of smoothing techniques for {ME} models},
  journal =      {IEEE Transactions on Speech and Audio Processing},
  year =     2000,
  volume =   8,
  number =   1
}


@Book{Chentsov1982,
  author =   {N. N. {\v C}encov},
  title =    {Statistical Decision Rules and Optimal Inference},
  publisher =    {American Mathematical Society},
  year =     1982
}




@Article{Cohen1999,
  author =   {William C. Cohen and Robert E. Schapire and Yoram Singer},
  title =    {Learning to Order Things},
  journal =      {Journal of Artificial Intelligence Research},
  volume = 10,
  pages = {243-270},
  year =     {1999},
}



@InProceedings{Collins2000,
  author =   {M. Collins and  R. E. Schapire and Y. Singer},
  title =    {Logistic regression, {AdaBoost and Bregman distances}},
  booktitle =    {Computational Learning Theory},
 year =      2000
}

@Article{Collins2002,
  author =   {M. Collins and  R. E. Schapire and Y. Singer},
  title =    {Logistic regression, {AdaBoost and Bregman distances}},
  journal =      {Machine Learning},
  volume = 48,
  year =     {2002}
}




@InProceedings{Colonius1993,
  author =   {Hans Colonius},
  title =    {Complete Concensus and Order Independence: Relating Ranking and Choice},
  booktitle =    {Probability Models and Statistical Analysis for Ranking Data,
{Fligner & Verducci Eds.}},
  year =     1993
}

@inproceedings{Cramer00,
  author = {Kobi Cramer and Yoram Singer},
  title = {On the Learnability and Design of Output Codes for Multiclass Problems},
  booktitle = {Computational Learning Theory},
  year = 2000
}

@InProceedings{Crammer2001,
  author =   {Koby Crammer and Yoram Singer},
  title =    {Pranking with Ranking},
  booktitle =    {Advances in Neural Information Processing Systems},
  year =     2001
}

@Article{Crammer2002,
  author =   {K. Crammer and Y. Singer},
  title =    {On the Learnability and Design of Output Codes for Multiclass Problems},
  journal =      {Machine Learning},
  year =     2002,
  volume =   47
}
@inproceedings{joachims:01,
 author = "Thorsten Joachims and Nello Cristianini and John Shawe-Taylor",
 title = "Composite kernels for hypertext categorisation",
 booktitle = "Proceedings of the International Conference on Machine Learning (ICML)",
 year = "2001",
}
@InProceedings{Craven1998,
  author =   {M. Craven and D. DiPasquo and D. Freitag and A. McCallum and T. Mitchell and K. Nigam and S. Slattery.},
  title =    {Learning to Extract Symbolic Knowledge from the World Wide Web},
  booktitle =    {Proceedings of the 15th National Conference on Artificial Intelligence},
  year =     1998
}

@Book{Critchlow1985,
  author =   {D. E. Critchlow},
  title =    {Metric Methods for Analyzing Partially Ranked Data},
  publisher =    {Lecture Notes in Statistics, volume 34, Springer},
  year =     {1985},
}



@Article{Critchlow1992,
  author =   {D. E. Critchlow and J. S. Verducci},
  title =    {Detecting a Trend in Paired Rankings},
  journal =      {Journal of the Royal Statistical Society C},
  volume =  {41},
  number =      {1},
  pages =       {17-29},
  year =     1992
}

@Article{Csiszar1975,
  author =   {Imre Csisz\'{a}r},
  title =    {{I}-divergence geometry of probability distributions and minimization problems},
  journal =      {The Annals of Probability},
  year =     1975,
  volume =   3
}

@Article{Csiszar1991,
  author =   {Imre Csisz\'{a}r},
  title =    {Why Least Squares and Maximum Entropy? {An} Axiomatic Approach to Inference for Linear Inverse Problems},
  journal =      {The Annals of Statistics},
  year =     1991,
  volume =   19,
  number =   4
}


@Article{Cutler1996,
  author =   {A. Cutler and O. I. Cordero-Brana},
  title =    {Minimum Hellinger Distance Estimation for Finite Mixture Models},
  journal =      {Journal of the {American} {Statistical} {Association}},
  year =     1996,
  volume =   91,
  pages =    {1716-1723}
}

@Article{Darroch1972,
  author =   {J. N. Darroch and D. Ratcliff},
  title =    {Generalized iterative scaling for log-linear models},
  journal =      {The Annals of Mathematical Statistics},
  year =     1972
}



@Article{Dawid1975,
  author =   {A. P. Dawid},
  title =    {Discussion of {Efron}'s paper},
  journal =      {The Annals of Statistics},
  year =     1975,
  volume =   3
}

@Article{Dawid1977,
  author =   {A. P. Dawid},
  title =    {Further Comments on Some Comments on a Paper by Bradley Efron},
  journal =      {The Annals of Statistics},
  year =     1977,
  volume =   5
}

@Manual{DellaPietra1993,
  title =    {Statistical modelling by ME},
  author =   {S. Della Pietra and V. Della Pietra},
  year =     1993,
  note =     {IBM internal report}
}





@article{DellaPietra1997,
  author = {S. {Della Pietra} and V. {Della Pietra} and J. Lafferty},
  title = {Inducing Features of Random Fields},
  journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence},
  number = 4,
  volume = 19,
  year = 1997
}

@TechReport{DellaPietra2001,
  author =   {S. {Della Pietra} and V. {Della Pietra} and J. Lafferty},
  title =    {Duality and Auxiliary Functions for {Bregman} Distances},
  institution =  {Carnegie Mellon University},
  year =     {2001},
  number =   {CMU-CS-01-109},
}

@Book{Devroye2001,
  author =   {Luc Devroye and G{\'a}bor Lugosi},
  title =    {Combinatorial Methods in Density Estimation},
  publisher =    {Springer-Verlag},
  year =     {2001},
  address =      {New York},
}

@article{Diaconis+Graham:77,
  author={Persi Diaconis and R. L. Graham},
  title={Spearman's Footrule as a Measure of Disarray},
  journal={Journal of the Royal Statistical Society, Series B},
  volume={39},
  number={2},
  year={1977},
  pages={262--268},
}




@article{Diaconis+Hanlon:92,
  author = {Persi Diaconis and Phil Hanlon},
  title = {Eigen Analysis for Some Examples of the {M}etropolis Algorithm},
  journal = {Contemporary Mathematics},
  volume = {138},
  year = {1992},
  pages = {99--117},
}

@Book{Diaconis:88,
  author =   {Persi Diaconis},
  title =    {Group Representations in Probability and Statistics},
  publisher =    {Institute of Mathematical Statistics},
  year =     {1988},
}

@article{Diaconis:89,
  author = {Persi Diaconis},
  title = {A Generalization of Spectral Analysis with Application to Ranked Data},
  journal = {Annals of Statistics},
  volume= {17},
  number={3},
  year={1989},
  month={Sept.},
  pages={949--979},
}

@article{Dietterich95a,
  author = {T. G. Dietterich and G. Bakiri},
  title = {Solving Multiclass Learning Problems via Error-Correcting Codes},
  journal = jair,
  year = 1995,
  volume = 2,
  pages = {263-286},
}

@InProceedings{Domingos2000,
  author =   {Pedro Domingos},
  title =    {Bayesian Averaging of Classifiers and the Overfitting Problem},
  booktitle =    icml17,
  pages =    {223-230},
  year =     2000
}

@Article{Donoho1988,
  author =   {D. L. Donoho and R. C. Liu},
  title =    {The ``Automatic'' Robustness of Minimum Distance Functionals},
  journal =      {Annals of Statistics},
  year =     1988,
  volume =   16,
  number =   2,
  pages =    {552-586}
}
@inproceedings{Duffy+Helmbold:00,
  author = {N. Duffy and D. Helmbold},
  title = {Potential Boosters?},
  booktitle = {Advances in Neural Information Processing Systems},
  year = 2000,
}
@Article{Efron1975,
  author =   {Bradley Efron},
  title =    {Defining the Curvature of a Statistical Problem},
  journal =      {The Annals of Statistics},
  year =     1975,
  volume =   3,
  number =   6
}

@Article{Efron1996,
  author =   {Bradley Efron and Robert Tibshirani},
  title =    {Using Specially Designed Exponential Families for Density Estimation},
  journal =      {Annals of Statistics},
  year =     1996,
  volume =   24,
  number = 6,
  pages =    {2431-2461}
}
@Article{Feigin1978,
  author =   {Paul Feigin and Ayala Cohen},
  title =    {On a Model for Concordance Between Judges},
  journal =      {Journal of the Royal Statistical Society B},
  year =     1978,
  volume =   40,
  pages =    {203-213}
}
@InCollection{Feigin1992,
  author =   {P. D. Feigin},
  title =    {Modeling and Analyzing Paired Ranking Data},
  booktitle =    {Probability Models and Statistical Analyses for Ranking Data},
  year =     {1992},
  editor = {M. A. Fligner and J. S. Verducci},
  publisher =   {Springer}
}
@Article{Ferguson1973,
  author =   {Thomas S. Ferguson},
  title =    {A Bayesian analysis of some nonparametric problems},
  journal =      {The Annals of Statistics},
  year =     1973,
  volume =   1,
  number =   4,
  pages =    {209-230}
}

@Article{Ferguson1974,
  author =   {Thomas S. Ferguson},
  title =    {Prior distributions on spaces of probability measures},
  journal =      {The Annals of Statistics},
  year =     1974,
  volume =   2,
  number =   4,
  pages =    {615-629}
}

@Article{Fligner1986,
  author =   {M. A. Fligner and J. S. Verducci},
  title =    {Distance Based Ranking Models},
  journal =      {Journal of the Royal Statistical Society B},
  volume = 43,
  pages = {359-369},
  year =     1986
}

@Article{Fligner1988,
  author =   {M. A. Fligner and J. S. Verducci},
  title =    {Multistage Ranking Models},
  journal =      {Journal of the American Statistical Association},
  volume = 83,
  pages = {892-901},
  year =     1988
}

@Article{Fligner1990,
  author =   {M. A. Fligner and J. S. Verducci},
  title =    {Posterior probabilities for a Concensus Ordering},
  journal =      {Psychometrika},
  volume =      {55},
  pages =        {53-63},
  year =     1990,
}

@Book{Fligner1993,
  ALTauthor =    {},
  editor =   {M. A. Fligner and J. S. Verducci},
  title =    {Probability Models and Statistical Analyses for Ranking Data},
  publisher =    {Springer-Verlag},
  year =     {1993},
}

@Article{Foote2000,
  author =   {Richard Foote and Gagan Mirchdani and Daniel Rockmore and Dennis Healy and Tim Olson},
  title =    {A Wreath product group approach to signal and image processing: Part 1 - multiresolution analyis},
  journal =      {IEEE Transactions on Signal Processing},
  year =     2000,
  volume =   48
}
@inproceedings{Freund1996,
    author = {Y. Freund and R. E. Schapire},
    title = "Experiments with a new Boosting algorithm",
    booktitle = "International Conference on Machine Learning",
    year = 1996,
}

@InProceedings{DellaPietra1992,
  author =   {Stephen Della-Pietra and  Vincent Della-Pietra and Robert Mercer and Salim Rukos},
  title =    {Adaptive Language Modeling Using Minimum Discriminat Estimation},
  booktitle =    {Proc. of the International Conference on Accoustics, Speech and Signal Processing},
  year =     1992
}

@Article{Rosenfeld1996,
  author =   {Ronald Rosenfeld},
  title =    {A Maximum Entropy Approach to Adaptive Statistical Language Modeling},
  journal =      {Computer, Speech and Language },
  year =     1996,
  volume =   10
}

@InProceedings{Freund1998,
  author =   {Yoav Freund and Raj Iyer and Robert E. Schapire and Yoram Singer},
  title =    {An efficient boosting algorithm for combining preferences},
  booktitle =    {International Conference on Machine Learning},
  year =     {1998},
}
@Article{Friedman2000,
  author =   {Jerome Friedman and Trevor Hastie and Robert Tibshirani},
  title =    {Additive logistic regression: A statistical view of boosting},
  journal =      {The Annals of Statistics},
  volume = 28,
  number = 2,
  pages = {337-374},
  year =     2000
}


@Article{Friedman97,
  author =   {N. Friedman and  D. Geiger and M. Goldszmidt},
  title =    {Bayesian Network Classifiers},
  journal =      {Machine Learning},
  year =     1997
}
@Book{Gill1981,
  author =   {P. E. Gill and W. Murray and M. H. Wright},
  title =    {Practical Optimization},
  publisher =    { Academic Press},
  year =     {1981},
}
@PhdThesis{Gous1998,
  author =   {A. Gous},
  title =    {Exponential and Spherical Subfamily Models},
  school =   {Stanford University},
  year =     1998
}
@PhdThesis{Grasselli2001,
  author =   {Matheus R. Grasselli},
  title =    {Classical and Quantum Information Geometry},
  school =   {King's College, London},
  year =     2001
}
@inproceedings{Lauritzen:87,
  author = {Stefan L. Lauritzen},
  title = "Statistical manifolds",
  booktitle = "Differential Geometry in Statistical Inference",
  editor = "S. I. Amari and O. E. Barndorff-Nielsen and  R. E. Kass and
            S. L. Lauritzen and C. R. Rao",
  pages = "163--216",
  publisher = "Institute of Mathematical Statistics, Hayward, CA",
  year = "1987",
}
@article{Grigoryan98,
  author = {Alexander Grigor'yan and Masakazu Noguchi},
  title = {The heat kernel on hyperbolic space},
  journal = {Bulletin of the London Mathematical Society},
  volume = {30},
  year = {1998},
  pages = {643--650}
}

@Article{Guo2002,
  author =   {Y. Guo and P. L. Bartlett and J. Shawe-Taylor and R. C. Williamson},
  title =    {Covering Numbers for Support Vector Machines},
  journal =      {IEEE Transaction on Information Theory},
  year =     2002,
  volume =   48,
  number =   1
}
@InProceedings{Hall2000,
  author =   {K. Hall and T. Hofmann},
  title =    {Learning Curved Multinomial Subfamilies for Natural Language Processing and Information Retrieval},
  booktitle =    {Proc. of the 17th International Conference on Machine Learning},
  year =     2000
}
@book{Haykin1999,
  author = { Simon Haykin},
  title = {Neural Networks a Comprehensive Foundations},
  publisher = {Prentice Hall},
  year = 1999,
  edition = {second}
}
@Article{Heckerman2000,
  author =   {David Heckerman and David Maxwell Chickering and Christopher Meek and Robert Rounthwaite and Carl Kadie},
  title =    {Dependency Networks for Inference, Collaborative Filtering, and Data Visualization},
  journal =      {Journal of Machine Learning Research},
  volume = 1,
  year =     2000
}

@Article{Hoeting1999,
  author =   {Jennifer Hoeting, David Madigan, Adrian Raftery and Chris Volinsky},
  title =    {Bayesian model averaging},
  journal =      {Statistical Science},
  year =     1999
}


@InProceedings{Hofmann2000,
  author =   {T. Hofmann and J. Puzicha},
  title =    {Latent class models for collaborative filtering},
  booktitle =    {Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence},
  year =     {2000},
}


@Article{Ikeda2004,
  author =   {Shiro Ikeda and Toshiyuki Tanaka and Shunichi Amari},
  title =    {Stochastic Reasoning, Free Energy, and Information Geometry},
  journal =      {Neural Computation},
  year =     {2004},
  volume = 16,
  number = 9
}
@InProceedings{Jaakkola1998,
  author =   {T. Jaakkola and D. Haussler},
  title =    {Exploiting Generative Models in Discriminative Classifiers},
  booktitle =    {Advances in Neural Information Processing Systems, 11},
  year =     1998
}

@techreport{Jaakola99a,
  author = {Tommi Jaakola and Marina Meila and Tony Jabara},
  title = {Maximum Entropy Discrimination},
  institution = "MIT",
  number = "AITR-1668",
  year = 1999
}

@phdthesis{James98,
  author = {Gareth James},
  title = {Majority Vote Classifiers: Theory and Applications},
  school = {Stanford University},
  year = {1998}
}

@InProceedings{Joachims1999,
  author =   {T. Joachims},
  title =    {Transductive inference for text classification using support vector machines},
  booktitle =    {Machine Learning: Proceedings of the 16th International Conference},
  year =     1999
}
@Article{Kass1989,
  author =   {R. E. Kass},
  title =    {The Geometry of Asymptotic Inference},
  journal =      {Statistical Science},
  year =     1989,
  volume =   4,
  number =   3,
  pages = {188-234}
}

@Book{Kass1997,
  author =   {R. E. Kass and P. W. Voss},
  title =    {Geometrical Foudnation of Asymptotic Inference},
  publisher =    {John Wiley \& Sons, Inc},
  year =     1997
}

@article{Kendall1938,
  author =   {M. G. Kendall},
  title =    {A new measure of rank correlation},
  year =     {1938},
  journal =      {Biometrika},
  volume =   30,
}
@Book{Khinchin1957,
  author =   {A. I. Khinchin},
  title =    {Mathematical Foundations of Information Theory},
  publisher =    {Dover Publications},
  year =     1957
}

@inproceedings{Kivinen1999,
    author = "J. Kivinen and M. K. Warmuth",
    title = "Boosting as entropy projection",
    booktitle = "{Proceedings of the 20th Annual Conference
on Computational Learning Theory}",
    year = 1999
}

@Book{Kullback1968,
  author =   {Solomon Kullback},
  title =    {Information Theory and Statistics},
  publisher =    {Dover publications},
  year =     {1968},
}

@Book{Boyd2004,
  author =   {Stephen Boyd and Lieven Vandenberghe},
  title =    {Convex Optimization},
  publisher =    {Cambridge University Press},
  year =     2004
}

@Article{Atkinson1981,
  author =   {C. Atkinson and A. F. Mitchell},
  title =    {Rao's distance measure},
  journal =      {Sankhya: {The Indian} Journal of Statistics, A},
  year =     1981,
  volume =   43
}

@InProceedings{Lafferty01a,
  author =   {John Lafferty and  Fernando Pereira and Andrew McCallum},
  title =    {Conditional Random Fields: Probabilistic models for segmenting and labeling sequence data},
  booktitle =    {International Conference on Machine Learning},
  year =     2001
}

@Article{Lafferty1988,
  author =   {John Lafferty},
  title =    {The Density Manifold and Configuration Space Quantization},
  journal =      {Transactions of the American Mathematical Society},
  year =     1988,
  volume =   305,
  number =   2
}

@InProceedings{Lafferty1999,
    author = "John Lafferty",
    title = "Additive Models, Boosting, and Inference for Generalized Divergences",
    booktitle = "{Proceedings of the 20th Annual Conference
on Computational Learning Theory}",
    year = 1999
}
@InProceedings{Lafferty2003,
  author =   {John Lafferty and Guy Lebanon},
  title =    {Information Diffusion Kernels},
  booktitle =    {Advances in Neural Information Processing, 15},
 year = {2003},
 publisher = {MIT press}
}
@ARTICLE{Brody1998,
  AUTHOR       = {D. C. Brody and L. P. Houghston},
  TITLE        = {Statistical Geometry in Quantum Mechanics},
  YEAR         = {1998},
  JOURNAL      = {Proc. of the Royal Society: Mathematical, Physical and Engineering Sciences},
  volume       = {454},
  number       = {1977}
}
@ARTICLE{Barndorff1983,
  AUTHOR       = {O. Barndorff-Nilsen and P. Bl{\ae}sild},
  TITLE        = {Exponential Models with Affine Dual Foliations},
  YEAR         = {1983},
  JOURNAL      = {The Annals of Statistics},
  volume       = {11},
  number       = {3}
}
@ARTICLE{Barndorff1986,
  AUTHOR       = {O. E. Barndorff-Nilsen},
  TITLE        = {Likelihood and Observed Geometries},
  YEAR         = {1986},
  JOURNAL      = {The Annals of Statistics},
  volume       = {14},
  number       = {3}
}
@ARTICLE{Barndorff1993,
  AUTHOR       = {O. Barndorff-Nilsen and P. Bl{\ae}sild},
  TITLE        = {Orthogeodesic Models},
  YEAR         = {1993},
  JOURNAL      = {The Annals of Statistics},
  volume       = {21},
  number       = {2}
}



@ARTICLE{Stein1955,
  AUTHOR       = {Charles Stein},
  TITLE        = {Inadmissability of the usual estimator estimator for the mean of a multivariate normal distribution},
  YEAR         = {1955},
  JOURNAL      = {Proc. Third Berkeley Symp. Math. Statist. Prob.},
}
@ARTICLE{Efron1977,
  AUTHOR       = {B. Efron and C. N. Morris},
  TITLE        = {Stein's paradox in statistics},
  YEAR         = {1977},
  JOURNAL      = {Scientific American},
  volume       = {236},
}

@BOOK{Schervish1995,
  AUTHOR       = {Mark J. Schervish},
  TITLE        = {Theory of Statistics },
  YEAR         = {1995},
  PUBLISHER    = {Springer},
}

@ARTICLE{Casella1985,
  AUTHOR       = {George Casella},
  TITLE        = {An Introduction to Empirical Bayes Data Analysis},
  YEAR         = {1985},
  JOURNAL      = {The American Statistician},
  volume       = {39},
  number       = {2},
}
@ARTICLE{Robbins1955,
  AUTHOR       = {H. Robbins},
  TITLE        = {An Empirical Bayes Approach to Statistics},
  YEAR         = {1955},
  JOURNAL      = {Proc. Third Berkeley Symp. Math. Statist. Prob.},
}

@ARTICLE{Lafferty2004,
  AUTHOR       = {John Lafferty and Guy Lebanon},
  TITLE        = {Diffusion Kernels on Statistical Manifolds},
  YEAR         = {(accepted)},
  JOURNAL      = {Journal of Machine Learning Research},
}

@InProceedings{Lanckriet2002,
  author = {G. R. G. Lanckriet and P. Bartlett and N. Cristianini and L. El Ghaoui and M. I. Jordan},
  title =    {Learning the Kernel Matrix with Semidefinite Programming},
  booktitle =    {International Conf. on Machine Learning},
  year =     2002
}
@unpublished{Bartlett:02b,
  author = "Peter L. Bartlett and Olivier Bousquet and Shahar Mendelson",
  title  = "Local {R}ademacher Complexities",
  note = "Manuscript",
  year = "2003",
}
@inproceedings{LiYau:80,
  author = "Peter Li and Shing-Tung Yau",
  title = "Estimates of Eigenvalues of a compact {R}iemannian manifold",
  booktitle = "Geometry of the Laplace Operator",
  series = "Proceedings of Symposia in Pure Mathematics",
  volume = "36",
  year="1980",
  pages="205--239",
}
@article{Berger:71,
  author = "Marcel Berger and Paul Gauduchon and Edmond Mazet",
  title = "Le spectre d'une variet\'{e} {R}iemannienne",
  journal = "Lecture Notes in Mathematics",
  volume = "Vol. 194, {\rm Springer-Verlag}",
  year = "1971",
}

@article{Mendelson:03,
  author = {Shahar Mendelson},
  title = {On the Performance of Kernel Classes},
  journal = {Journal of Machine Learning Research},
  volume = "4",
  pages = "759--771",
  year = "2003",
}
@article{Bartlett:02,
  author = {Peter L. Bartlett and Shahar Mendelson},
  title = {Rademacher and {G}aussian complexities: {R}isk bounds and
   structural results},
  journal = {Journal of Machine Learning Research},
  volume = "3",
  pages = "463--482",
  year = "2002",
}
@Book{Lang1999,
  author =   {Serge Lang},
  title =    {Fundamentals of Differential Geometry},
  publisher =    {Springer},
  year =     1999
}

@InProceedings{Lebanon2001a,
  author =   {Guy Lebanon and John Lafferty},
  title =    {Boosting and Maximum likelihood for Exponential models},
  booktitle =    {Advances in Neural Information Processing Systems, 14},
  year =     {2002},
  publisher = {MIT press}
}

@TechReport{Lebanon2001b,
  author =   {Guy Lebanon and John Lafferty},
  title =    {Boosting and Maximum likelhood for Exponential models},
  institution =  {Carnegie Mellon University},
  year =     2001,
  number =   {CMU-CS-01-144}
}


@InProceedings{Lebanon2001c,
  author =   {Guy Lebanon and Alfred Bruckstein},
  title =    {Designing Moir\'{e} Patterns},
  booktitle =    {Energy Minimization Methods in Computer Vision and Pattern Recognition,
Lecture Notes in Computer Science, Vol. 2134},
  year =     {2001},
  publisher = {Springer}
}

@Article{Lebanon2001d,
  author =   {Guy Lebanon and Alfred Bruckstein},
  title =    {Variational Approach to Moir\'{e} Pattern Synthesis},
  journal =      {Journal of the Optical Society of America},
  year =     2001,
  volume =   18,
  number =   6
}


@InProceedings{Lebanon2002a,
  author =   {Guy Lebanon and John Lafferty},
  title =    {Cranking: Combining Rankings Using  Conditional Probability
Models on Permutations},
  booktitle =    {Proc. of the 19th International Conference on Machine Learning},
  year =     {2002},
  publisher = {Morgan Kaufmann Publishers}
}
@inProceedings{Moreno:03,
  author    = "Pedro J. Moreno and Purdy P. Ho and Nuno Vasconcelos",
  title     = "A {K}ullback-{L}eibler divergence based kernel for {SVM}
               classification in multimedia applications",
  booktitle = "Advances in Neural Information Processing Systems 16",
  year      = "2004"
}
@InProceedings{Lebanon2003,
  author =   {Guy Lebanon and John Lafferty},
  title =    {Conditional Models on the Ranking Poset},
  booktitle =    {Advances in Neural Information Processing Systems, 15},
  year =     {2003},
}

@InProceedings{Lebanon2003b,
  author =   {Guy Lebanon},
  title =    {Learning {Riemannian} Metrics},
  booktitle =    {Proc. of the 19th Conference on Uncertainty in Artificial Intelligence},
  year =     {2003},
  publisher =    {Morgan Kaufmann Publishers}
}
@TechReport{Lebanon2003c,
  author =   {Guy Lebanon},
  title =    {Computing the Volume Element of a Family of Metrics on the Multinomial Simplex},
  institution =  {Carnegie Mellon University},
  year =     {2003},
  number =   {CMU-CS-03-145}
}
@InProceedings{Lebanon2004a,
  author =   {Guy Lebanon},
  title =    {An Extended \v{C}encov Characterization of Conditional Information Geometry},
  booktitle =    {Proc. of the 20th Conference on Uncertainty in Artificial Intelligence},
  year =     {2004},
  publisher = {AUAI press},
}
@InProceedings{Lebanon2004b,
  author =   {Guy Lebanon and John Lafferty},
  title =    {Hyperplane Margin Classifiers on the Multinomial Manifold},
  booktitle =    {Proc. of the 21st International Conference on Machine Learning},
year =   2004,
   publisher = {ACM press}
}
@ARTICLE{lebanon2005a,
  AUTHOR       = {Guy Lebanon},
  TITLE        = {Axiomatic Geometry of Conditional Models},
  YEAR         = {to appear},
  JOURNAL      = {IEEE Transactions on Information Theory}
}


@Book{Lee1997,
  author =   {John M. Lee},
  title =    {Riemannian Manifolds, An Introduction to Curvature},
  publisher =    {Springer},
  year =     1997
}




@Book{Lee2000,
  author =   {John M. Lee},
  title =    {Introduction to Topological Manifolds},
  publisher =    {Springer},
  year =     2000
}

@Book{Lee2002,
  author =   {John M. Lee},
  title =    {Introduction to Smooth Manifolds},
  publisher =    {Springer},
  year =     2002
}

@InProceedings{Belkin:2003,
  author =   {Mikhail Belkin and Partha Niyogi},
  title =    {Using Manifold Structure for Partially Labeled Classification },
  booktitle =    {Advances in Neural Information Processing Systems },
   year =    2003
}

@inproceedings{Lewis94
 ,author = "David D. Lewis and Marc Ringuette"
 ,title = "A Comparison of Two Learning Algorithms for Text Categorization"
 ,booktitle = "Symposium on Document Analysis and Information Retrieval"
 ,year = 1994
 ,pages = "81--93"
}

@PhdThesis{Li1999,
  author =   {Qiang Li},
  title =    {Estimation of mixture models},
  school =   {Department of Statistics, Yale University},
  year =     1999,
  month =    {May}
}

@Article{Lindsay1994,
  author =   {B. G. Lindsay},
  title =    {Efficiency Versus Robustness: The Case for Minimum Hellinger Distance and Related Methods},
  journal =      {Annals of Statistics},
  year =     1994,
  volume =   22,
  number =   2,
  pages =    {1081-1114}
}
@Article{Madigan1994,
  author =   {David Madigan, Adrian E. Raftery},
  title =    {Model selection and accounting for model uncertainty in graphical models using Occam's window},
  journal =      {Journal of the American Statistical Association},
  year =     1994,
  volume =   89,
  number =   428
}

@Article{Mallows1957,
  author =   {C. L. Mallows},
  title =    {Non-Null Ranking Models},
  journal =      {Biometrika},
  year =     1957,
volume = 44,
pages = {114-130}
}
@InCollection{Malsen1991,
  author =   {David K. Malsen and Daniel N. Rockmore},
  title =    {Generalized {FFT}s - A survey of some recent results},
  booktitle =    {DIMACS series in discrete mathematics and theoretical
computer science},
  year =     {1997},
  editor =   {L. Finkelstein and W. Kantor},
  volume =   {28},
}

@Book{Marden1996,
  author =   {J. I. Marden},
  title =    {Analyzing and modeling rank data},
  publisher =    {CRC Press},
  year =     1996
}

@inproceedings{Mason:99,
  author={L. Mason and J. Baxter and P. Bartlett and M. Frean},
  title={Functional gradient techniques for combining hypotheses},
  booktitle={Advances in Large Margin Classifiers},
  editor={A. Smola and P. Bartlett and B. Sch{\"o}lkopf and D. Schuurmans},
  year=1999,
}
@Book{McCullagh1989,
  author =   {P. McCullagh and J. A. Nelder},
  title =    {Generalized Linear Models},
  publisher =    {Chapman \& Hall/CRC},
  year =     1989,
  edition =      {Second}
}
@inproceedings{Mccallum1998,
    author = {Andrew McCallum and Ronald Rosenfeld and Tom Mitchell and Andrew Y. Ng},
    title = {Improving text classification by shrinkage in a hierarchy of classes},
    booktitle = "Proc. 15th International Conf. on Machine Learning",
    publisher = "Morgan Kaufmann, San Francisco, CA",
    pages = "359--367",
    year = "1998",
}
@book{Mitchell97,
  author = {Tom M. Mitchel},
  title = {Machine Learning},
  publisher = {McGraw-Hill},
  year = 1997
}

@Book{Murray1993,
  author =   {M. K. Murray and J. W. Rice},
  title =    {Differential Geometry and Statistics},
  publisher =    {CRC Press},
  year =     1993
}

@InProceedings{Ng2001,
  title =    {On Discriminative vs. Generative classifiers: A comparison of logistic regression and naive Bayes},
  author = {A. Y. Ng and M. I. Jordan},
  booktitle = {Advances in Neural Information Processing Systems},
  year =     2001
}

@InProceedings{Nigam1999,
  author =   {K. Nigam and J. Lafferty and A. McCallum},
  title =    {Using maximum entropy for text classification},
  booktitle =    {International Joint Conference on Artificial Intelligence},
  year =     1999
}

@Article{Nigam2000,
  author =   {Kamal Nigam and Andrew McCallum and Sebastian Thrun and Tom Mitchell},
  title =    {Text Classification from Labeled and Unlabeled Documents using EM},
  journal =      {Machine Learning},
  year =     2000,
  volume =   39,
  pages =    {103-134}
}
@PhdThesis{Nigam2001,
  author =   {Kamal Nigam},
  title =    {Using Unlabeled Data to Improve Text Classification},
  school =   {Carnegie Mellon University},
  year =     2001
}
@inproceedings{OSullivan:98,
author = {J. A. O'Sullivan},
title  = {Alternating Minimization Algorithms: {F}rom {Blahut-Arimoto} to
         {E}xpectation-{M}aximization},
editor = {A. Vardy},
booktitle = {Codes, Curves, and Signals: Common Threads in Communications},
year = {1998},
pages = {173-192},
}
@InProceedings{Pennock2000,
  author =   {D. M. Pennock and E. Horvitz and S. Lawrence and C. L. Giles},
  title =    {Collaborative filtering by personality diagnosis: A hybrid memory- and model-based approach},
  booktitle =    {Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence },
  year =     {2000},
}

@Article{Pistone1995,
  author =   {Giovanni Pistone and Carlo Sempi},
  title =    {An Infinite-Dimensional Geometric Structure on the Space of all the Probability Measures Equivalent to a Given One},
  journal =      {The Annals of Statistics},
  year =     1995,
  volume =   23,
  number =   5
}
@PhdThesis{Ponte1998,
  author =   {Jay Ponte},
  title =    {A language modelling approach to information retrieval},
  school =   {Univeristy of Massachusetts, Amherst},
  year =     1998
}
@InProceedings{Popescul2001,
  author =   {Alexandrin Popescul and Lyle H. Ungar and David M. Pennock and Steve Lawrence},
  title =    {Probabilistic Models for Unified Collaborative Filtering and Content Based Recommendation in Sparse-Data Environments },
  booktitle =    {Uncertainty in Artificial Intelligence},
  year =     2001
}
@InProceedings{Popescul2002,
  author =   {A. Popescul and L. H. Ungar and D. M. Pennock and S. Lawrence},
  title =    {Probabilistic models for unified collaborative and content-based recommendation in sparse-data environments},
  booktitle =    {Proceedings of the 17th Conference on Uncertainty in Artificial Intelligence},
  year =     {2001},
}

@Article{Rao1945,
  author =   {C. R. Rao},
  title =    {Information and accuracy attainable in the estimation of statistical parameters},
  journal =      {Bulletin of the Calcutta Mathematical Society},
  year =     1945,
  volume =   37
}
@inproceedings{Resnick1994,
 author = {P. Resnick and N. Iacovou and M. Suchak and P. Bergstrom and J. Riedl},
 title = {GroupLens: an open architecture for collaborative filtering of netnews},
 booktitle = {Proceedings of the Conference on Computer Supported Cooperative Work},
 year = {1994},
 }

@InCollection{Rockmore1991,
  author =   {Daniel N. Rockmore},
  title =    {Some applications of generalized {FFT}s},
  booktitle =    {DIMACS series in discrete mathematics and theoretical
computer science},
  year =     {1997},
  editor =   {L. Finkelstein and W. Kantor},
  volume =   {28},
}


@book{Rosenberg:97,
  title = "The {L}aplacian on a {R}iemannian Manifold",
  author = "Steven Rosenberg",
  publisher = "Cambridge University Press",
  year = {1997},
}

@InProceedings{Rosenfeld1997a,
  author =   {Ronald Rosenfeld},
  title =    {A Whole Sentence Maximum Entropy Language Model},
  booktitle =    { Proc. IEEE workshop on Automatic Speech
     Recognition and Understanding},
  year =     1997
}

@InProceedings{Rosenfeld1999a,
  author =   {Ronald Rosenfeld and Larry Wasserman and Can Cai and Xiaojin Zhu},
  title =    {Interactive Feature Induction and Logistic Regression for Whole Sentence Exponential Language Models},
  booktitle =    {Proc. IEEE workshop on Automatic Speech Recognition and Understanding},
  year =     1999
}
@Article{Roweis2000,
  author =   {S. Roweis and L. Saul},
  title =    {Nonlinear Dimensionality Reduction by Locally Linear Embedding.},
  journal =      {Science},
  year =     2000,
  volume =   290
}
@Book{Salton1983,
  author =   {G. Salton and M. J. McGill},
  title =    {Introduction to Modern Information Retrieval},
  publisher =    {McGraw Hill},
  year =     1983
}

@InProceedings{Saul1997,
  author =   {L. K. Saul and M. I. Jordan},
  title =    {A variational principle for model-based interpolation},
  booktitle =    {Advances in Neural Information Processing Systems 9},
  year =     1997
}


@Article{Schapire1990,
  author =   {R. E. Schapire},
  title =    {The strength of weak learnability},
  journal =      {Machine Learning},
  year =     1990,
  key =      2,
  volume =   5
}

@Article{Schapire1999,
  author =   {Robert E. Schapire and Yoram Singer},
  title =    {Improved Boosting Algorithms Using Confidence-rated Predictions},
  journal =      {Machine Learning},
  year =     1999
}

@InProceedings{Schapire2002,
  author =   {R. E. Schapire},
  title =    {The boosting approach to machine learning: An overview},
  booktitle =    {MSRI Workshop on Nonlinear Estimation and Classification},
  year =     2002
}

@inproceedings{Schapire97a,
  author = {Robert E. Schapire},
  title = {Using Output Correcting Codes to Boost Multiclass Learning Problems},
  booktitle = icml14,
  year = 1997
}
@inproceedings{Schapire99a,
  author = {Robert E. Schapire},
  title = {A Brief Introduction to Boosting},
  booktitle = ijcai16,
  year = 1999
}


@Book{Schoen1994,
  author =   {R. Schoen and S. Yau},
  title =    {Lectures on Differential Geometry},
  publisher =    {International Press},
  series = {Conference Proceedings and Lecture Notes in Geometry and Topology},
  volume = 1,
  year =     1994
}
@book{Nelson:68,
    author = "Edward Nelson",
    title  = "Tensor Analysis",
    publisher = "Princeton University Press",
    year = "1968",
}
@unpublished{Dietterich:02,
  author = {Tom Dietterich},
  title = "{{AI} {S}eminar}",
  note = "Carnegie {M}ellon",
  year = {2002},
}
@book{Milnor:63,
  title = "Morse Theory",
  author = "John W. Milnor",
  publisher = "Princeton University Press",
  location = "Princeton, NJ",
  year = "1963",
}

@Article{Shahshahani1979,
  author =   {S. Shahshahani},
  title =    {A new mathematical framework for the study of linkage and selection},
  journal =      {Memoirs of the American Mathematical Society},
  year =     1979,
  volume =   17,
  number =   211
}
@Article{Smith1950,
  author =   {B. Babington Smith},
  title =    {Discussion of Professor {Ross's} paper},
  journal =      {Journal of the Royal Statistical Society B},
  volume = 12,
  number = 1,
  pages = {41-59},
  year =     1950
}
@Book{Spivak1975,
  author =   {M. Spivak},
  title =    {A Comprehensive Introduction to Differential Geometry},
  publisher =    {Publish or Perish},
  year =     1975,
  volume = {1-5}
}

@Book{Stanley1986,
  author =   {R. P. Stanley},
  ALTeditor =    {},
  title =    {Enumerative Combinatorics},
  publisher =    {Wadsworth \& Brooks/Cole Mathematics Series},
  year =     {1986},
  volume =   {1},
}

@InProceedings{Szummer2002,
  author =   {M. Szummer and T. Jaakkola},
  title =    {Partially labeled classification with Markov random walks},
  booktitle =    {Advances in Neural Information processing systems, 14 },
  year =     2002
}


@InProceedings{Szummer2003,
  author =   {M. Szummer and T. Jaakkola},
  title =    {Information regularization with partially labeled data},
  booktitle =    {Advances in Neural Information processing systems, 15},
  year =     2003
}


@Article{Tamura1986,
  author =   {R. N. Tamura and D. D. Boos},
  title =    {Minimum Hellinger Distance Estimation for Multivariate Location and Covariance},
  journal =      {Journal of the American Statistical Association},
  year =     1986,
  volume =   81,
  number =   393,
  pages =    {223-229}
}


@Article{Tenenbaum2000,
  author =   {J. B. Tenenbaum and V. deSilva and J. C. Langford},
  title =    {A Global Geometric Framework for Nonlinear Dimensionality Reduction},
  journal =      {Science},
  year =     2000,
  volume =   290,
  pages =    {2319-2323}
}

@Article{Thurstone1927,
  author =   {L. L. Thurstone},
  title =    {A Law of Comparative Judgement},
  journal =      {Psychological Review},
  volume =  34,
  pages = {273-286},
  year =     1927
}
@article{Poggio:90,
  author = {Tomaso Poggio and Frederico Girosi},
  title = {Regularization algorithms for learning that are equivalent to
       multilayer networks},
  journal = {Science},
  volume = {247},
  pages = {978--982},
  year = {1990},
}
@InProceedings{Toutanova2001,
  author =   {Kristina Toutanova and Francine Chen and Kris Popat and Thomas Hofmann},
  title =    {Text Classification in a Hierarchical Mixture Model for Small Training Sets },
  booktitle =    {Proceedings 10th International Conference on Information and Knowledge Management},
  year =     2001
}

@misc{UCI,
 author = {C.L. Blake and C.J. Merz},
     title = {The {UCI} Repository of Machine Learning Databases},
     note={University of California, Irvine, Department of Information
     and Computer Sciences, 1998.
{\tt http://www.ics.uci.edu/\raise.6ex\hbox{$\scriptstyle\sim\,$}mlearn/{MLR}epository.html}},
 year = 1998
}
@article{Zhang:01,
  author = {Tong Zhang and Frank J. Oles},
  title = {Text categorization based on regularized linear classification methods},
  journal = {Information Retrieval},
  volume = "4",
  issue = {1},
  pages = "5--31",
  month = {April},
  year = "2001",
}
@Book{Vapnik2000,
  author =   {Vladimir N. Vapnik},
  title =    {The Nature of Statistical Learning Theory},
  publisher =    {Springer},
  year =     {2000},
  edition =      {Second},
}
@book{Vapnik98,
  author = {Vladimir N. Vapnik},
  title = {Statistical Learning Theory},
  publisher = {John Wiley \& Sons},
  year = 1998
}


@Article{Vogt1999,
  author =   {C. C. Vogt and G. W. Cottrell},
  title =    {Fusion Via a Linear Combination of Scores},
  journal =      {Information Retrieval},
  volume = 1,
  number = 3,
  pages = {151-173},
  year =     1999
}

@Book{Whittaker1990,
  author =   {Joe Whittaker},
  title =    {Graphical models in applied multivariate analysis},
  publisher =    {John Wiley and sons},
  year =     {1990}
}

@InProceedings{Xing2003,
  author =   {E. P. Xing and A. Y. Ng and M. I. Jordan and S. Russel},
  title =    {Distance Metric Learning with Applications to Clustering with Side Information},
  booktitle =    {Advances in Neural Information Processing Systems, 15},
  year =     2003,
}
@article{Yang1999,
    author = {Yiming Yang},
    title = {An evaluation of statistical approaches to text categorization},
    journal = {Information Retrieval},
    volume = 1,
    pages = {69-90},
    year = 1999,
}
@Article{Yang2002,
  author =   {Yiming Yang and S. Slattery and R. Ghani},
  title =    {A study of approaches to
     hypertext categorization},
  journal =      {Information Retrieval},
  year =     "To Appear"
}

@Article{Yates1937,
  author =   {F. Yates},
  title =    {The design and analysis of factorial experiments},
  journal =      {Imp. Bur. Soil Sci. Tech. Comm.},
  year =     1937,
  number =   37
}


@Article{Zhang2001,
  author =   {Tong Zhang and Frank J. Oles},
  title =    {Text Categorization Based on Regularized Linear Classification Methods},
  journal =      {Information Retrieval},
  year =     2001,
  volume =   4,
  number =   1,
  pages =    {5-31}
}

@InProceedings{deSilva2003,
  author =   {V. de Silva and J. B. Tenenbaum},
  title =    {Local versus global methods for nonlinear dimensionality reduction},
  booktitle =    {Advances in Neural Information Processing Systems 15},
  year =     2003
}

@inproceedings{manmatha01,
  author = "R. Manmatha and T. Rath and F. Feng",
  title = "Modeling score distributions for combining the outputs of search engines",
  booktitle="Proc. of the 24th ACM SIGIR
    conference",
  year = "2001",
}