Schedule

12/4/1998 – Morning Session

Chair: Dale Schuurmans

  • 07:30-07:55 Leo Breiman

  • 07:55-08:15 Yoram Singer

  • 08:15-08:35 Florence d'Alche-Buc

  • 08:35-08:50 Grigoris Karakoulas

  • 08:50-09:05 Coffee Break

  • 09:05-09:20 Bernhard Schölkopf

  • 09:20-09:40 Takashi Onoda

  • 09:40-09:55 John Baxter

  • 09:55-10:10 Peter Bartlett

  • 10:10-10:30 Nello Cristianini

12/4/1998 – Afternoon Session

Chair: Peter Bartlett

  • 16:00-16:20 Dale Schuurmans

  • 16:20-16:40 Manfred Warmuth

  • 16:40-16:55 Yoav Freund

  • 16:55-17:10 Thilo Frieß

  • 17:10-17:25 Qun Zhao

  • 17:25-17:40 Pal Rujan

  • 17:40-17:45 Coffee Break

  • 17:45-19:00 Organized Panel Discussion

12/5/1998 – Morning Session

Chair: Alex Smola

  • 07:30-08:30 Tutorial on Mathematical Programming – Olvi Mangasarian

  • 08:30-08:50 Kristin Bennett

  • 08:50-09:05 Coffee Break

  • 09:05-09:25 Ralf Herbrich

  • 09:25-09:45 David Stork

  • 09:45-10:00 Chris Burges

  • 10:00-10:15 Grace Wahba

  • 10:15-10:30 Joachim Buhmann

12/5/1998 – Afternoon Session

Chair: Bernhard Schökopf

  • 16:00-16:25 Vladimir Vapnik

  • 16:25-16:40 Jason Weston

  • 16:40-17:00 Leonid Gurvits

  • 17:00-17:25 Alex Smola

  • 17:25-17:40 Coffee Break

  • 17:40-17:55 Manfred Opper

  • 17:55-18:10 Ole Winter

  • 18:10-18:25 Adam Kowalzyk

  • 18:25-18:40 John Platt

  • 18:40-19:00 Wrap Up Session

Speakers

  • Florence d'Alche-Buc, Laboratoire d'Informatique de Paris 6, Paris
    Estimated margin data for Boosting and SVM

  • Peter Bartlett, Australian National University
    Error Estimates for Large Margin Classifiers

  • Jonathan Baxter, Australian National University
    Nearest neighbour classification and large margins

  • Kristin Bennett, Rensslaer Polytechnic Institute
    Enlarging the Margins in Perceptron Decision Trees

  • Leo Breiman, Stanford University
    Are margins relevant in voting?

  • Joachim Buhmann, Universität Bonn
    Empirical Risk Approximation for Unsupervised Learning

  • Chris Burges, Lucent Technologies
    Discriminative Gaussian Mixture Models

  • Nello Cristianini, University of Bristol
    Margin Distribution Bounds on Generalization

  • Yoav Freund, AT&T Research
    Large Margin Classification Using the Perceptron Algorithm

  • Thilo Frieß, GMD Berlin
    Support Vector Neural Networks

  • Leonid Gurvits, NEC Research
    A note on a scale-sensitive dimension of linear bounded functionals in Banach spaces

  • David Stork, CRC Ricoh, Isabelle Guyon, Clopinet
    What linear discriminant techniques teach us about SVMs

  • Ralf Herbrich, TU Berlin
    Large Margin Rank Boundaries for Preference Learning

  • Grigoris Karakoulas, Global Analytics, CIBC
    Boosting Regressors

  • Adam Kowalczyk, Trevor Anderson, Telstra Research Laboratories
    Local training of support vector machines

  • Olvi Mangasarian, University of Madison
    Mathematical Programming in Machine Learning

  • Takashi Onoda, CRIEPI, Gunnar Rätsch, GMD FIRST
    nu-AdaBoost Classification

  • Manfred Opper, NCRG, Aston University
    Statistical Mechanics of Support Vector Learning

  • John Platt, Microsoft Research
    Making Support Vector Machines Yield Probabilities

  • Pal Rujan, University of Oldenburg
    Computing the Bayes Support Vector Machine

  • Bernhard Schölkopf, GMD FIRST
    Reparametrizing SV Machines

  • Dale Schuurmans, University of Waterloo
    General linear ensemble methods for learning

  • Yoram Singer, AT&T Research
    Boosted Vector Machines

  • Alex Smola, GMD FIRST
    Entropy Numbers, Operators, and Kernels

  • Vladimir Vapnik, AT&T Research
    Error Bounds for Support Vector Machines

  • Grace Wahba, University of Madison
    A look at Structural Risk Minimization, Generalized Approximate Cross Validation, and the Generalized Degrees of Freedom for Signal

  • Manfred Warmuth, UC Santa Cruz
    Hinge Loss and Average Margins for Predicting with Linear Threshold Functions with Applications to Boosting

  • Jason Weston, Royal Holloway, London
    Predictive power of bounds and stacking support vector machines

  • Ole Winther, Theoretical Physics, University of Lund
    Mean Field Algorithms for Gaussian Process Classification and Support Vector Machines

  • Qun Zhao, University of Florida
    Automatic Target Recognition with Support Vector Machines