Abstract: In the present paper,we investigate the learning rates of regularized regression with sample dependent hypothesis and p-loss. We show the robustness of the solutions with respect to the probability distributions, with which we provide the sample error. Also,we show the approximation error with a kind of K−functional whose convergence rates are described in possibility. Finally, we show the explicit learning rates in cases of the norm regularization and the coefficient regularization. The results show that the parameters p have influences on the learning rates.
DOI: *As the DOI is a unique identifier, it is already available in the pdf version. **The DOI link will be activated in the first midst of January 2026.
Sheng Baohuai, Yu Wangke, Ye Peixin, Han Yongjie, "Learning Rates of Regularized Regression with p-loss," WSEAS Transactions on Mathematics, vol. 12, pp. -, 2013, DOI:
Sheng Baohuai, Yu Wangke, Ye Peixin, Han Yongjie. Learning Rates of Regularized Regression with p-loss.
WSEAS Transactions on Mathematics. 2013;12:-.