A Unified Loss Function in Bayesian Framework for Support Vector Regression

In this paper, we propose a unified non-quadratic loss function for regression known as soft insensitive loss function (SILF). SILF is a flexible model and possesses most of the desirable characteristics of popular non-quadratic loss functions, such as Laplacian, Huber's and Vapnik's -insensitive loss function. We describe the properties of SILF and illustrate our assumption on the underlying noise model in

• Type: Conference
• Year: 2001
• Where: ICML
• Authors: Wei Chu, S. Sathiya Keerthi, Chong Jin Ong
• Keywords: -insensitive Loss Function, ICML 2001, Insensitive Loss Function, Machine Learning, Non-quadratic Loss Function