Approximation of Unbiased Convex Classification Error Rate Estimator

作者：Gvardinskas Mindaugas^*; Tamosiunaite Minija

来源：Information Technology and Control, 2016, 45(2): 148-155.

DOI：10.5755/j01.itc.45.2.12052

• Error estimation
• Classification
• Resubstitution
• Cross-validation
• Bootstrap

Convex classification error rate estimator is described as weighted combination of the low-biased estimator and the high-biased estimator. If the underlying data model is known, the coefficients (weights) can be optimized so that the bias and root-mean-square error of the estimator is minimized However, in most situations, data model is unknown. In this paper we propose a new error estimation method, based on approximation of unbiased convex error rate estimator. Experiments with real world and synthetic data sets show that common error estimation methods, such as resubstitution, repeated 10-fold cross-validation, leave-one-out and random subsampling are outperformed (in terms of root-mean-square error) by the proposed method.

• 出版日期2016