| Autor: |
Mey, Alexander, Viering, Tom, Loog, Marco |
| Rok vydání: |
2019 |
| Předmět: |
|
| Druh dokumentu: |
Working Paper |
| DOI: |
10.1007/978-3-030-44584-3_26 |
| Popis: |
Manifold regularization is a commonly used technique in semi-supervised learning. It enforces the classification rule to be smooth with respect to the data-manifold. Here, we derive sample complexity bounds based on pseudo-dimension for models that add a convex data dependent regularization term to a supervised learning process, as is in particular done in Manifold regularization. We then compare the bound for those semi-supervised methods to purely supervised methods, and discuss a setting in which the semi-supervised method can only have a constant improvement, ignoring logarithmic terms. By viewing Manifold regularization as a kernel method we then derive Rademacher bounds which allow for a distribution dependent analysis. Finally we illustrate that these bounds may be useful for choosing an appropriate manifold regularization parameter in situations with very sparsely labeled data. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
