| Hedging Structured Concepts | 23 | 1.52 | 2010 |
| Gaussian clusters and noise: an approach based on the minimum description length principle | 1 | 0.40 | 2010 |
| Mixed Bregman Clustering with Approximation Guarantees | 21 | 1.24 | 2008 |
| Online Bayes point machines | 0 | 0.34 | 2003 |
| Channel equalization and the Bayes point machine | 0 | 0.34 | 2003 |
| Computational Learning Theory, 15th Annual Conference on Computational Learning Theory, COLT 2002, Sydney, Australia, July 8-10, 2002, Proceedings | 21 | 4.43 | 2002 |
| Online learning of linear classifiers | 5 | 1.28 | 2002 |
| Large Margin Classification for Moving Targets | 8 | 5.15 | 2002 |
| Relative loss bounds for multidimensional regression problems | 64 | 22.64 | 2001 |
| Boosting as entropy projection | 61 | 11.94 | 1999 |
| Averaging Expert Predictions | 40 | 5.72 | 1999 |
| Exponentiated gradient versus gradient descent for linear predictors | 286 | 70.76 | 1997 |
| The perceptron algorithm versus winnow: linear versus logarithmic mistake bounds when few input variables are relevant | 29 | 7.51 | 1997 |
| Learning Reliably and with One-Sided Error | 0 | 0.34 | 1995 |
| Worst-Case Loss Bounds For Single Neurons | 5 | 5.89 | 1995 |
| Tight worst-case loss bounds for predicting with expert advice | 48 | 43.94 | 1995 |
| Approximate inference of functional dependencies from relations | 118 | 8.22 | 1995 |
| Additive versus exponentiated gradient updates for linear prediction | 127 | 38.42 | 1995 |
| The perceptron algorithm vs. Winnow: linear vs. logarithmic mistake bounds when few input variables are relevant | 26 | 43.79 | 1995 |
| An algorithm for learning hierarchical classifiers | 0 | 0.34 | 1994 |
| The power of sampling in knowledge discovery | 67 | 12.78 | 1994 |
| Learning hierarchical rule sets | 11 | 1.00 | 1992 |
| Approximate Dependency Inference from Relations | 48 | 63.10 | 1992 |
| Reliable and Useful Learning with Uniform Probability Distributions | 1 | 0.36 | 1990 |
| Reliable and useful learning | 1 | 0.39 | 1989 |
