The quickhull algorithm for convex hulls
ACM Transactions on Mathematical Software (TOMS)
Rigorous learning curve bounds from statistical mechanics
Machine Learning - Special issue on COLT '94
Learning in Neural Networks: Theoretical Foundations
Learning in Neural Networks: Theoretical Foundations
STOC '84 Proceedings of the sixteenth annual ACM symposium on Theory of computing
Computable Shell Decomposition Bounds
The Journal of Machine Learning Research
Quantitatively tight sample complexity bounds
Quantitatively tight sample complexity bounds
Predicting (0, 1)-functions on randomly drawn points
SFCS '88 Proceedings of the 29th Annual Symposium on Foundations of Computer Science
Exact combinatorial bounds on the probability of overfitting for empirical risk minimization
Pattern Recognition and Image Analysis
A combinatorial approach to hypothesis similarity in generalization bounds
Pattern Recognition and Image Analysis
Hi-index | 0.00 |
We consider a problem of supervised statistical learning for a finite population and obtain PAC generalization bounds within the combinatorial PAC framework. Combinatorial counterparts of Langford shell bounds are obtained and are shown to be either the particular case of the Occam razor bound or a variant of Vapnik-Chervonenkis bound and similarly loose in both cases. The reasons for looseness of shell bounds are analyzed, the bounds are compared experimentally.