The L1/2 regularization method for variable selection in the Cox model

- We propose a L1/2 penalized Cox model.
- We develop a coordinate descent algorithm with a new univariate half thresholding operator.
- The L1/2 penalized Cox model is able to reduce the size of the predictor even further at moderate costs for the prediction accuracy.
- The L1/2 penalized Cox model is suitable for survival analysis with the high dimensional biological data.