Author(s)

Zhefeng Wang, Wanzhou Ye

Department of Mathematics, College of Science, Shanghai University, Shanghai, China.

In this paper, we propose a Smooth Quantile Boost Classification (SQBC) algorithm for binary classification problem. The SQBC algorithm directly uses a smooth function to approximate the “check function” of the quantile regression. Compared to other boost-based classification algorithms, the proposed algorithm is more accurate, flexible and robust to noisy predictors. Furthermore, the SQBC algorithm also can work well in high dimensional space. Extensive numerical experiments show that our proposed method has better performance on randomly simulations and real data.

Boosting, Quantile Regression, Smooth Check Function, Binary Classification

Wang, Z. and Ye, W. (2016) An Efficient Smooth Quantile Boost Algorithm for Binary Classification. Advances in Pure Mathematics, 6, 615-624. doi: 10.4236/apm.2016.69050.