Robust and Smooth Wave Loss Function for Advancing Supervised Learning: A Novel Approach
The authors propose a novel asymmetric loss function called the "wave loss function" that exhibits robustness against outliers, insensitivity to noise, and smoothness characteristics. By integrating this wave loss function into the least squares setting of Support Vector Machines (SVM) and Twin Support Vector Machines (TSVM), the authors introduce two new models: Wave-SVM and Wave-TSVM, respectively.