Loading...
Please wait, while we are loading the content...
Similar Documents
Multiclass Learning Approaches: A Theoretical Comparison with Implications
| Content Provider | CiteSeerX |
|---|---|
| Author | Sabato, Sivan Shalev-Shwartz, Shai Daniely, Amit |
| Abstract | We theoretically analyze and compare the following five popular multiclass classification methods: One vs. All, All Pairs, Tree-based classifiers, Error Correcting Output Codes (ECOC) with randomly generated code matrices, and Multiclass SVM. In the first four methods, the classification is based on a reduction to binary classification. We consider the case where the binary classifier comes from a class of VC dimension d, and in particular from the class of halfspaces over R d. We analyze both the estimation error and the approximation error of these methods. Our analysis reveals interesting conclusions of practical relevance, regarding the success of the different approaches under various conditions. Our proof technique employs tools from VC theory to analyze the approximation error of hypothesis classes. This is in contrast to most previous uses of VC theory, which only deal with estimation error. 1 |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Theoretical Comparison Binary Classifier Vc Theory Practical Relevance Error Correcting Output Code Binary Classification Tree-based Classifier Popular Multiclass Classification Method Vc Dimension Code Matrix Analysis Reveals Interesting Conclusion Hypothesis Class Various Condition Proof Technique Different Approach Previous Us Multiclass Svm Multiclass Learning Approach Approximation Error Estimation Error |
| Content Type | Text |
