Learning Rates of Regression with q-norm Loss and Threshold

2017/01/08 by Hu, Ting, Yao, Yuan
#FOS: Mathematics #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.1701.01956

Abstract

This paper studies some robust regression problems associated with the q-norm loss (q≥1) and the ε-insensitive q-norm loss in the reproducing kernel Hilbert space. We establish a variance-expectation bound under a priori noise condition on the conditional distribution, which is the key technique to measure the error bound. Explicit learning rates will be given under the approximation ability assumptions on the reproducing kernel Hilbert space.

Related

• Optimality of Robust Online Learning
• Estimates on Learning Rates for Multi-Penalty Distribution Regression
• Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration
• Regularized least squares learning with heavy-tailed noise is minimax optimal
• Reproducing Kernel Hilbert Spaces for Penalized Regression: A Tutorial