Learnability and the Vapnik-Chervonenkis dimension
Journal of the ACM (JACM)
Cause-effect relationships and partially defined Boolean functions
Annals of Operations Research
Surveys in combinatorics, 1993
Classification by polynomial surfaces
Discrete Applied Mathematics
Accuracy of techniques for the logical analysis of data
Discrete Applied Mathematics - Special issue on the satisfiability problem and Boolean functions
Learning in Neural Networks: Theoretical Foundations
Learning in Neural Networks: Theoretical Foundations
Rademacher and gaussian complexities: risk bounds and structural results
The Journal of Machine Learning Research
Generalization Error Bounds for Threshold Decision Lists
The Journal of Machine Learning Research
Estimation of Dependences Based on Empirical Data: Springer Series in Statistics (Springer Series in Statistics)
Spanned patterns for the logical analysis of data
Discrete Applied Mathematics - Special issue: Discrete mathematics & data mining II (DM & DM II)
Accelerated algorithm for pattern detection in logical analysis of data
Discrete Applied Mathematics - Special issue: Discrete mathematics & data mining II (DM & DM II)
Hi-index | 0.04 |
This paper analyzes the predictive performance of standard techniques for the 'logical analysis of data' (LAD), within a probabilistic framework. It does so by bounding the generalization error of related polynomial threshold functions in terms of their complexity and how well they fit the training data. We also quantify the predictive accuracy in terms of the extent to which there is a large separation (a 'large margin') between (most of) the positive and negative observations.