Abstract | ||
---|---|---|
Obtaining accurate bounds of the probability of overfitting is a fundamental question in statistical learning theory. In this paper we propose exact combinatorial bounds for the family of classifiers making a lattice. We use some lattice properties to derive the probability of overfitting for a set of classifiers represented by concepts. The extent of a concept, in turn, matches the set of objects correctly classified by the corresponding classifier. Conducted experiments illustrate that the proposed bounds are consistent with the Monte Carlo bounds. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1007/978-3-319-59271-8_12 | Lecture Notes in Artificial Intelligence |
Keywords | Field | DocType |
Computational learning theory,Probability of overfitting,Lattice of classifiers | Statistical learning theory,Monte Carlo method,Lattice (order),Computer science,Pruning (decision trees),Artificial intelligence,Overfitting,Computational learning theory,Classifier (linguistics),Machine learning | Conference |
Volume | ISSN | Citations |
10308 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 5 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tatiana P. Makhalova | 1 | 3 | 5.10 |
Sergei O. Kuznetsov | 2 | 1630 | 121.46 |