D. Kuzmin, M. Warmuth. Unlabeled Compression Schemes for Maximum Classes talk.

D. Haussler, N. Littlestone and M. Warmuth. Predicting {0,1}-functions on randomly drawn points

Y. Li, P. Long and A. Srinivasan. Improved Bounds on the Sample Complexity of Learning

Y. Li, P. Long and A. Srinivasan. The 1-Inclusion Graph Algorithm is Near Optimal for the Prediction Model of Learning

D. Haussler and P. Long. A Generalization of Sauer's Lemma