Improved Classification Rates for Localized Algorithms under Margin Conditions. 1st ed. 2020
- 種類:
- 電子ブック
- 責任表示:
- by Ingrid Karin Blaschzyk
- 出版情報:
- Wiesbaden : Springer Fachmedien Wiesbaden : Imprint: Springer Spektrum, 2020
- 著者名:
- ISBN:
- 9783658295912 [3658295910]
- 注記:
- Introduction to Statistical Learning Theory -- Histogram Rule: Oracle Inequality and Learning Rates -- Localized SVMs: Oracle Inequalities and Learning Rates.
Support vector machines (SVMs) are one of the most successful algorithms on small and medium-sized data sets, but on large-scale data sets their training and predictions become computationally infeasible. The author considers a spatially defined data chunking method for large-scale learning problems, leading to so-called localized SVMs, and implements an in-depth mathematical analysis with theoretical guarantees, which in particular include classification rates. The statistical analysis relies on a new and simple partitioning based technique and takes well-known margin conditions into account that describe the behavior of the data-generating distribution. It turns out that the rates outperform known rates of several other learning algorithms under suitable sets of assumptions. From a practical point of view, the author shows that a common training and validation procedure achieves the theoretical rates adaptively, that is, without knowing the margin parameters in advance. Contents Introduction to Statistical - ローカル注記:
- 学内専用E-BOOKS (local access only)
類似資料:
Springer International Publishing : Imprint: Birkhäuser |
Springer International Publishing : Imprint: Springer |
Springer Berlin Heidelberg : Imprint: Springer |
Springer International Publishing : Imprint: Springer |
Springer Berlin Heidelberg : Imprint: Springer |
Springer London : Imprint: Springer |
Springer Berlin Heidelberg : Imprint: Springer |
Springer Nature Singapore : Imprint: Springer |
Springer International Publishing : Imprint: Springer |
Springer Milan : Imprint: Springer |
Springer International Publishing : Imprint: Springer |
Springer Netherlands : Imprint: Springer |