@article{abr-tfpf-64
, author =       "M. A. Aizerman, E. M. Braverman and  L. I. Rozonoer"
, title =        "Theoretical foundations of the potential function method in pattern
recognition learning"
, journal =        "Automation and Remote Control"
, volume = 25             
, pages = "821--837"
, year = 1964
}

@article{ass-unify-00
, author =       "E. L. Allwein, R. E. Schapire and Y. Singer"
, title =        "Reducing multiclass to binary: a unifying approach for margin
classifiers"
, journal =        "Journal of Machine Learning Research"
, volume = 1             
, pages = "113--141"
, year = 2000
}

@article{A88
, author =       "D. Angluin"
, title =        "Queries and concept learning"
, journal =        "Machine Learning"
, volume =  2      
, number =   4    
, pages = "319--342"
, year = 1988
}

@Book{ab-book-99,
  author =       "M. Anthony and P. Bartlett",
  title =        "Neural Network Learning: Theoretical Foundations", 
  publisher =    "CMU",
  year =         "1999"
}

@article{acg-ascolla-00
, author =       "P. Auer, N. Cesa Bianchi and C. Gentile"
, title =        "Adaptive and self-confident on-line learning algorithms"
, journal =        "Journal of Computer and System Sciences"
, notes = "forthcoming. Preliminary version in 
{\em Proceedings of 13th Annu. Conf. on Comput. Learning Theory},
pages 107--117, Palo Alto, CA, 2000"
}

@TechReport{uci,
  author =       "C. Blake, E. Keogh and  C. Merz",
  title =        "UCI repository of machine learning databases",
  institution =  "Dept. of Information
and Computer Sciences, University of California, Irvine",
  year =         "1998",
  note = "http://www.ics.uci.edu/$\sim$mlearn/MLRepository.html"
}

@article{b-pmbf-62
, author =       "H. D. Block"
, title =        "The perceptron: A model for brain functioning"
, journal =        "Reviews of Modern Physics"
, volume =  34       
, pages = "123--135"
, year =  1962
}

@article{cv-svn-95
, author =       "C. Cortes and V. Vapnik"
, title =        "Support-vector networks"
, journal =        "Machine Learning"
, volume =   20     
, number =   3    
, pages = "273--297"
, year = 1995
}

@Book{cst-book-00,
  author =       "N. Cristianini and J. Shawe-Taylor",
  title =        "An introduction to support vector machines and other kernel-based 
learning methods",
  publisher =    "Cambridge University Press",
  year =         "2000"
}

@InProceedings{dkr-emnlp-97,
  author =       "I. Dagan, Y. Karov and D. Roth",
  title =        "Mistake-Driven Learning in Text Categorization",
  booktitle =    "Proceedings of 2nd Conference on Empirical Methods in Natural Language Processing",
  publisher =    "Association for Computational Linguistics, 
Somerset, New Jersey",
  year =         "1997",
  pages =        "55--63"
}

@article{db-ecoc-95
, author =       "T. G. Dietterich and G. Bakiri"
, title =        "Solving multiclass learning problems via error-correcting output codes"
, journal =        "Journal of Artificial Intelligence Research"
, volume =  2        
, pages = "263--286"
, year = 1995
}

@Book{dh-pcsa-73,
  author =       "R. O. Duda and P. E. Hart",
  title =        "Pattern Classification and Scene Analysis",
  publisher =    "Wiley",
  year =         "1973"
}

@article{fs-lmcupa-99
, author =       "Y. Freund and R. E. Schapire"
, title =        "Large margin classification using the perceptron algorithm"
, journal =        "Journal of Machine Learning"
, volume =    37    
, number =    3   
, pages = "277--296"
, year = 1999
}

@InProceedings{fcc-98,
  author =       "T.-T. Friess, N. Cristianini and  C. Campbell",
  title =        "The kernel adatron algorithm: 
a fast and simple learning procedure for support vector machines",
  booktitle =    "Proceedings of 15th International Conference in Machine Learning",
  publisher =    "Morgan Kaufmann, San Mateo, CA",
  year =         "1998",
  pages =        "188--196"
}

@InProceedings{gl-99,
  author =       "C. Gentile and N. Littlestone",
  title =        "The robustness of the $p$-norm algorithms",
  booktitle =    "Proc. 12th Annu. Conf. on Comput. Learning Theory",
  publisher =    "ACM",
  year =         "1999",
  pages =        "1--11"
}

@Unpublished{gw-lhlam-98,
  author =       "C. Gentile and M. K. Warmuth",
  title =        "Linear Hinge Loss and Average margin",
  year =         "2001",
  note =         "Unpublished. Preliminary version in
{\em Proc. Advances in Neural Information Processing Systems 11},
pages 225--231, MIT Press, Cambridge, MA, 1999"
}

@InProceedings{g-alma-00,
  author =       "C. Gentile",
  title =        "A new approximate maximal margin classification algorithm",
  booktitle =    "T. K. Leen, T. G. Dietterich, and V. Tresp editors, 
Advances in Neural Information Processing Systems 13",
  publisher =    "MIT Press, Cambridge, MA",
  year =         "2001",
  pages =        "500--506"
}

@InProceedings{gr-spell-96,
  author =       "A. R. Golding and D. Roth",
  title =        "Applying Winnow to Context-Sensitive Spelling Correction",
  booktitle =    "Proceedings of 13th International Conference in Machine Learning",
  publisher =    "Morgan Kaufmann, San Mateo, CA,",
  year =         "1996",
  pages =        "182--190"
}

@article{gls-gcrfldu-97
, author =       "A. J. Grove, N. Littlestone and D. Schuurmans"
, title =        "General convergence results for linear discriminant updates"
, journal =        "Journal of Machine Learning"
, volume =   43     
, number =    3   
, pages = "173--210"
, year = 2001
}

@article{hw-wl-95
, author =       "D. P. Helmbold and M. K. Warmuth"
, title =        "On weak learning"
, journal =        "Journal of Computer and System Sciences"
, volume =   50     
, number =   3  
, pages = "551--573"
, year = 1995
}

@InBook{j-svml-98},
  author =       "T. Joachims.",
  title =        "Making large-scale support vector machines learning practical",
  booktitle =    "B. Scholkopf, C. Burges and A. Smola (eds.):
Advances in kernel methods: support vector machines",
  publisher =    "MIT Press, Cambridge, MA",
  year =         "2000"
}

@TechReport{ksbm-99,
  author =       "S. S. Keerthi, S. K. Shevade,  C. Bhattacharyya and K.R.K. Murthy",
  title =        "A fast iterative nearest point algorithm for support vector machine classifier
design",
  institution =  "Indian Institute of Science, ISL-99-03",
  year =         "1999"
}

@article{kw-avegulp-97
, author =       "J. Kivinen and M. K. Warmuth"
, title =        "Additive versus exponentiated gradient updates for linear prediction"
, journal =        "Information and Computation"
, volume =   132      
, number =   1  
, pages = "1--64"
, year = 1997
}

@article{kw-rlbmrp-97
, author =       "J. Kivinen and M. K. Warmuth"
, title =        "Relative loss bounds for multidimensional regression problems"
, journal =        "Journal of Machine Learning"
, note = "forthcoming. Preliminary version in 
{\em Proc. Advances in Neural Information Processing Systems 10}, 
pages 287--293, MIT Press, Cambridge, MA, 1998"
}

@article{kwa-paw-98
, author =       "J. Kivinen, M. K. Warmuth and P. Auer"
, title =        "The perceptron algorithm vs. winnow: linear vs. logarithmic mistake
  bounds when few input variables are relevant"
, journal =        "Artificial Intelligence"
, volume =  97      
, pages = "325--343"
, year = 1997
}

@InBook{k-lmp-98,
  author =       "A. Kowalczyk",
  title =        "Maximal margin perceptron",
  booktitle =    "Smola, Bartlett, Scholkopf, and Schuurmans editors, 
Advances in large margin classifiers",
  publisher =    "MIT Press, Cambridge, MA",
  year =         "1999"
}

@article{lc-bahzcr-89, 
  author =       "Y. Le Cun, B. Boser, J. S. Denker, D. Henderson, 
                  R. E. Howard, W. Hubbard and L. J. Jackel", 
  title =        "Backpropagation applied to handwritten zip code recognition",
  journal =        "Neural Computation", 
  volume =  1, 
  pages = "541--551", 
  year = 1989
}

@InProceedings{lc-mnist-95,
  author =       "Y. Le Cun, L. J. Jackel, L. Bottou, A. Brunot, C. Cortes,  
J. S. Denker, H. Drucker, I. Guyon, U. Muller, S. Sackinger,  
P. Simard and  V. Vapnik",
  title =        "Comparison of learning algorithms for handwritten digit recognition",
  booktitle =    "Proceedings of ICANN 1995",
  year =         "1995",
  pages =        "53--60"
}

@PhdThesis{l-thesis-00,
  author =       "Y. Li",
  title =        "From support vector machines to large margin classifiers",
  school =       "Ph.D. thesis, School of Computing, National University of Singapore",
  year =         "2000"
}

@article{ll-romma-99
, author =       "Y. Li and P. Long"
, title =        "The relaxed online maximum margin algorithm"
, journal =        "Journal of Machine Learning"
, note = "forthcoming. Preliminary version 
in {\em S. A. Solla, T. K. Leen and K. R. Muller editors, Advances in Neural
Information Processing Systems 12}, pages 498--504,
MIT Press, Cambridge, MA, 2000"
}

@article{l-liaanla-88
, author =       "N. Littlestone"
, title =        "Learning quickly when irrelevant attributes abound: 
{A} new linear-threshold algorithm"
, journal =        "Machine Learning"
, volume =  2         
, pages = "285--318"
, year = 1988
}

@article{lw-wma-94
, author =       "N. Littlestone and  M.~K. Warmuth"
, title =        "The weighted majority algorithm"
, journal =        "Information and Computation"
, volume =  108      
, number =   2    
, pages = "212--261"
, year = 1994
}

@article{m-mpdm-97
, author =       "O. Mangasarian"
, title =        "Mathematical programming in data mining"
, journal =        "Data Mining and Knowledge Discovery"
, volume =  42      
, number =  1     
, pages = "183--201"
, year = 1997
}

@article{m-msmps-68
, author =       "O. Mangasarian"
, title =        "Multi-surface method of pattern separation"
, journal =        "IEEE Trans. on Information Theory"
, volume =   14         
, pages = "801--807"
, year = 1968
}

@InProceedings{nns-93,
  author =       "P. Nachbar, J. A. Nossek and  J. Strobl",
  title =        "The generalized adatron algorithm",
  booktitle =    "Proceedings of 1993 IEEE ISCAS",
  year =         "1993",
  pages =        "2152--2155"
}

@InProceedings{n-cpp-62,
  author =       "A.~B.~J. Novikov",
  title =        "On convergence proofs on perceptrons",
  booktitle =    "Proc. of the Symposium on the Mathematical Theory of
Automata, vol. XII",
  year =         "1962",
  pages =        "615--622"
}

@InProceedings{ofg-97,
  author =       "E. Osuna, R. Freund and F. Girosi",
  title =        "An improved training algorithm for support vector machines",
  booktitle =    "Proceedings of IEEE NNSP'97",
  year =         "1997"
}

@InBook{p-98,
  author =       "J. C. Platt",
  title =        "Fast training of support vector machines using sequential
minimal optimization",
  booktitle =    "Scholkopf, Burges and Smola editors, 
Advances in kernel methods: support vector machines",
  publisher =    "MIT Press, Cambridge, MA",
  year =         "1998"
}

@InProceedings{pcst-dags-99,
  author =       "J. C. Platt, N. Cristianini and J. Shawe-Taylor",
  title =        "Large margin DAGs for multiclass classification",
  booktitle =    "S. A. Solla, T. K. Leen and K. R. Muller editors, Advances in Neural
Information Processing Systems 12",
  publisher =    "MIT Press, Cambridge, MA",
  year =         "1999",
  pages =        "547--553"
}

@Book{r-pn-62,
  author =       "F. Rosenblatt",
  title =        "Principles of neurodynamics: Perceptrons and the theory of
brain mechanisms", 
  publisher =    "Spartan Books, Washington, D.C.",
  year =         "1962"
}

@article{sfbs-bm-98
, author =       "R. E. Schapire, Y. Freund, P. Bartlett and W. S. Lee"
, title =        "Boosting the margin: A new explanation for the effectiveness of voting methods"
, journal =        "The Annals of Statistics"
, volume =  26      
, number =  5     
, pages = "1651--1686"
, year = 1998
}

@article{smbkmrs-ivf-99
, author =       "B. Scholkopf, S. Mika, C.J.C. Burges, P. Knirsch, 
                  K. Muller, G. Ratsch and A. Smola"
, title =        "Input space vs. feature space in kernel-based methods"
, journal =        "IEEE Trans. on Neural Network"
, volume =   10     
, number =    5   
, pages = "1000--1017"
, year = 1999
}

@article{ssbgnpv-svmcomp-97
, author =       "B. Scholkopf, K. Sung,  C.J.C. Burges,
F. Girosi, P. Niyogi, T. Poggio and V. Vapnik"
, title =        "Comparing support vector machines with gaussian kernels to
radial basis function classifiers"
, journal =        "IEEE Trans. on Signal Processing"
, volume =  45         
, pages = "2758--2765"
, year = 1997
}

@article{sb-bnn-00
, author =       "H. Schwenk and Y. Bengio"
, title =        "Boosting neural networks"
, journal =        "Neural Computation"
, volume =     12   
, number =      8 
, pages = "1869--1887"
, year = 2000
}

@InProceedings{s-pluw-99,
  author =       "R. A. Servedio",
  title =        "On PAC Learning Using Winnow, Perceptron, and a Perceptron-like Algorithm",
  booktitle =    "Proc. 12th Annu. Conf. on Comput. Learning Theory",
  publisher =    "ACM",
  year =         "1999",
  pages =        "296--307"
}

@article{stbwa-srmoddh-98
, author =       "J. Shawe-Taylor, P.  Bartlett, R. Williamson and M. Anthony"
, title =        "Structural Risk Minimization over Data-Dependent Hierarchies"
, journal =        "IEEE Trans. on Information Theory"
, volume =     44   
, number =      5  
, pages = "1926--1940"
, year = 1998
}

@InProceedings{sld-tr-93,
  author =       "P. Simard, Y. LeCun and J. Denker.",
  title =        "Efficient pattern recognition using a new transformation distance",
  booktitle =    "S. Hanson, J. Cowan, and L. Giles, editors, Advances in 
Neural Information Processing Systems, volume 5",
  publisher =    "Morgan Kaufmann",
  year =         "1993"
}

@Book{v-book-98,
  author =       "V. Vapnik",
  title =        "Statistical learning theory", 
  publisher =    "J. Wiley \& Sons, New York",
  year =         "1998"
}