STAT 593:
Machine Learning

Some Possible Readings for Spring Quarter 2000

• Martin Anthony and Peter L. Bartlett (1999). Neural Network Learning: Theoretical Foundations, Cambridge University Press, Cambridge.
• Marten Wegkamp and Nicholas Hengartner (2000). A note on model selection procedures in nonparametric classification.
• Model selection using Rademacher penalization, by Fernando Lozano, Electrical and Computer Engineering, University of New Mexico.
• Rademacher penalties and structural risk minimization. by Vladimir Koltchinskii, Department of Mathematics and Statistics, University of New Mexico.
• Statistical Learning Control of Uncertain Systems: It is better than it seems". by Vladimir Koltchinskii, C.T. Abdallah, M. Ariola, P. Dorato, and D. Panchenko, Departments of Mathematics and Computer Engineering, University of New Mexico.
• Rademacher processes and bounding the risk of function learning. V. Koltchinskii and D. Panchenko, Department of Mathematics and Statistics, University of New Mexico.
• Empirical margin distributions and bounding the generalization error of combined classifiers. V. Koltchinskii and D. Panchenko, Department of Mathematics and Statistics, University of New Mexico.

Some Links to Other Sites of Interest

• For the following papers, go to Schapire's web site:
  • R.E. Schapire and Y. Singer [to appear]. "Improved boosting algorithms using confidence-rated predictions," Machine Learning.
  • Y. Freund and R.E. Schapire [1997] "A decision-theoretic generalization of on-line learning and an application to boosting," Journal of Computer and System Sciences, 55(1):119-139.
  • L. Mason, J. Baxter, P. Bartlett and M. Frean [1999]. "Boosting algorithms as gradient descent in function space."
• For the following papers, go to Friedman's web site:
  • J.H. Friedman, T. Hastie, R. Tibshirani [2000]. "Additive Logistic Regression: a Statistical View of Boosting," Annals of Statistics.
  • J.H. Friedman [1999]. "Stochastic Gradient Boosting."
  • J.H. Friedman [1999]. "Greedy Function Approximation: A Gradient Boosting Machine."
• For Leo Breiman's papers on Arcing Classifiers, go to Breiman.