ASRL:A robust loss function with potential for development

Abstract--In this article, we proposed a partition-wise robust loss function (ASRL -Adapative segmented robust loss)based on the previous robust loss function. The characteristics of this loss function are that it achieves high robustness and a wide range of applicability through partition-wise design and adaptive parameter adjustment. Finally, the advantages and development potential of this loss function were verified by applying this loss function to the XGBoost and using five different datasets (with different dimensions, different sample numbers, and different fields) to compare with the XGBoost using other loss functions. The results of multiple experiments have proven the advantages of ASRL in MSE, MAE, R2, etc. ASRL's dynamic segmentation design and adaptive threshold make it more robust and can be applied to more fields, such as as a loss function for multimodal learning and reinforcement learning, and has a large room for development.The implementation code repository github link in this paper is:ASRLCODE Index Terms--ASRL,Robustness,MSE,MAE,Loss Function I. INTRODUCTION In regression prediction of machine learning, the loss function is the core tool to measure the difference between the model prediction value and the true value. Its role runs through the entire process of model training, optimization and evaluation.