Name
Abstract | ||
|---|---|---|
Teaching dimension is a learning theoretic quantity that specifies the minimum training set size to teach a target model to a learner. Previous studies on teaching dimension focused on version-space learners which maintain all hypotheses consistent with the training data, and cannot be applied to modern machine learners which select a specific hypothesis via optimization. This paper presents the first known teaching dimension for ridge regression, support vector machines, and logistic regression. We also exhibit optimal training sets that match these teaching dimensions. Our approach generalizes to other linear learners. |
Year | Venue | Keywords |
|---|---|---|
2015 | JOURNAL OF MACHINE LEARNING RESEARCH | Optimization based learner,Karush-Kuhn-Tucker conditions,VC-dimension |
Field | DocType | Volume |
Training set,Teaching dimension,Regression,Computer science,Support vector machine,Artificial intelligence,Logistic regression,Machine learning | Journal | 17 |
Issue | ISSN | Citations |
1 | 1532-4435 | 9 |
PageRank | References | Authors |
0.48 | 18 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ji Liu | 1 | 1352 | 77.54 |
| Xiaojin Zhu | 2 | 3586 | 222.74 |
| Hrag Ohannessian | 3 | 9 | 0.48 |