 | Blumer, A. -- Occam’s Razor - April 1987 |
| Helmbold, D. -- Learning nested differences of intersection-closed concept classes - 1989 |
| Blumer, A. -- Learnability and the Vapnik-Chervonenkis Dimension - 1989 |
| Warmuth, M. K. -- Towards Representation Independence in PAC-learning - October 1989 |
| Helmbold, D. -- Learning Nested Differences of Intersection Closed Concept Classes - 1990 |
| Pitt, L. -- Prediction Preserving Reducibility - December 1990 |
| Abe, N. -- Polynomial learnability of probabilistic concepts with respect to the Kullback-Leibler divergence - 1991 |
| Haussler, D. -- Equivalence of Models for Polynomial Learnability - December 1991 |
| Helmbold, D. P. -- Some weak learning results - 1992 |
| Helmbold, D. -- Learning Integer Lattices - 1992 |
| Haussler, D. -- The Probably Approximately Correct PAC and Other Learning Models - 1993 |
| Long, P. M. -- Composite Geometric Concepts and Polynomial Predictability - 1993 |
| Cesa-Bianchi, N. -- How to use expert advice - 1993 |
| Littlestone, N. -- The weighted majority algorithm - 1994 |
| Haussler, D. -- Predicting {0,1} Functions on Randomly Drawn Points - 1994 |
| Kivinen, J. -- Exponentiated Gradient Versus Gradient Descent for Linear Predictors - June 1994 |
| Cesa-Bianchi, N. -- Bounds on approximate steepest descent for likelihood maximization in exponential families - July 1994 |
| Cesa-Bianchi, N. -- Worst-case quadratic loss bounds for on-line prediction of linear functions by gradient descent - 1995 |
| Littlestone, N. -- On-line learning of linear functions - 1995 |
| Helmbold, D. -- On Weak Learning - June 1995 |
| Helmbold, D. -- A comparison of new and old algorithms for a mixture estimation problem - July 1995 |
| Helmbold, D. P. -- Worst-case Loss Bounds for Single Neurons - 1996 |
| Helmbold, D. P. -- Worst-Case Loss Bounds for Sigmoided Linear Neurons - 1996 |
| Auer, P. -- Exponentially many local minima for single neurons - 1996 |
